Papers
Thu 25 Sep 2025
491 papers
- Tiny but Mighty: A Software-Hardware Co-Design Approach for Efficient Multimodal Inference on Battery-Powered Small DevicesMultimodal LLMs / vision-language models → Visual token pruning and efficiency
- Ranking Before Serving: Low-Latency LLM Serving via Pairwise Learning-to-RankLLM reasoning → Test-time compute and efficient thinking +1
- Agentic-AI Healthcare: Multilingual, Privacy-First Framework with MCP AgentsLLM agents and tool use → Medical and scientific domain agents
- Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized LearningMixture-of-experts → MoE large language models +1
- Adaptive Federated Learning Defences via Trust-Aware Deep Q-NetworksLLM safety and security → Federated unlearning and poisoning
- In AI Sweet Harmony: Sociopragmatic Guardrail Bypasses and Evaluation-Awareness in OpenAI gpt-oss-20bLLM safety and security → Safety alignment, refusal and guardrails
- A Formal Comparison Between Chain of Thought and Latent ThoughtLLM reasoning → Prompting and chain-of-thought reasoning
- PALADIN: Self-Correcting Language Model Agents to Cure Tool-Failure CasesLLM agents and tool use → Tool learning and function calling
- Energy Guided Geometric Flow MatchingDiffusion models → Flow matching, time series and science
- Painless Activation Steering: An Automated, Lightweight Approach for Post-Training Large Language ModelsMechanistic interpretability → Activation steering methods
- CompareBench: A Benchmark for Visual Comparison Reasoning in Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
- PnP-CM: Consistency Models as Plug-and-Play Priors for Inverse ProblemsDiffusion models → Inverse problems and image restoration
- Regulating the Agency of LLM-based AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
- Bidirectional Intention Inference Enhances LLMs' Defense Against Multi-Turn Jailbreak AttacksLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
- Prompt-aware classifier free guidance for diffusion modelsDiffusion models → Image generation, text-to-image and editing
- DiaMoE-TTS: A Unified IPA-Based Dialect TTS Framework with Mixture-of-Experts and Parameter-Efficient Zero-Shot AdaptationMixture-of-experts → Multimodal MoE models
- Responsible Diffusion: A Comprehensive Survey on Safety, Ethics, and Trust in Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
- PACE: Physics Augmentation for Coordinated End-to-end Reinforcement Learning toward Versatile Humanoid Table TennisDeep reinforcement learning methods → RL for robot locomotion and manipulation
- SpecMER: Fast Protein Generation with K-mer Guided Speculative DecodingEfficient LLM inference and serving → Speculative decoding
- FlexMind: Supporting Deeper Creative Thinking with LLMsLLM reasoning → Reasoning benchmarks and evaluation
- Generating Stable Placements via Physics-guided Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics
- Logic of Hypotheses: from Zero to Full Knowledge in Neurosymbolic IntegrationLLM reasoning → Reasoning benchmarks and evaluation
- MMPlanner: Zero-Shot Multimodal Procedural Planning with Chain-of-Thought Object State ReasoningLLM reasoning → Spatial and embodied reasoning
- RED-DiffEq: Regularization by denoising diffusion models for solving inverse PDE problems with application to full waveform inversionDiffusion models → Flow matching, time series and science
- FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D PredictionWorld models → Video-generation world models and simulators
- DriftLite: Lightweight Drift Control for Inference-Time Scaling of Diffusion ModelsLLM reasoning → Diffusion reasoning and test-time scaling +1
- MobiLLM: An Agentic AI Framework for Closed-Loop Threat Mitigation in 6G Open RANsLLM agents and tool use → Agentic AI for wireless networks
- Guiding Audio Editing with Audio Language ModelDiffusion models → Audio, speech and music
- OjaKV: Context-Aware Online Low-Rank KV Cache CompressionEfficient LLM inference and serving → KV cache optimization
- VLCE: A Knowledge-Enhanced Framework for Image Description in Disaster AssessmentMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
- GeoEvolve: Automating Geospatial Model Discovery via Multi-Agent Large Language ModelsLLM agents and tool use → Multimodal and embodied agents
- Vision Language Models Cannot Plan, but Can They Formalize?Multimodal LLMs / vision-language models → Embodied and 3D vision-language models
- X-Streamer: Unified Human World Modeling with Audiovisual InteractionWorld models → World models for language agents
- No Alignment Needed for Generation: Learning Linearly Separable Representations in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- X-CoT: Explainable Text-to-Video Retrieval via LLM-based Chain-of-Thought ReasoningLLM reasoning → Multimodal reasoning
- AutoClimDS: Climate Data Science Agentic AI -- A Knowledge Graph is All You NeedLLM agents and tool use → Multimodal and embodied agents
- Learning GUI Grounding with Spatial Reasoning from Visual FeedbackLLM reasoning → Multimodal reasoning
- Correct Reasoning Paths Visit Shared Decision PivotsLLM reasoning → Prompting and chain-of-thought reasoning
- ControlHair: Synergizing Physics Simulator and Video Diffusion for Controllable Dynamic Hair RenderingDiffusion models → 3D, point cloud and scene generation
- Patch-Based Diffusion for Data-Efficient, Radiologist-Preferred MRI ReconstructionDiffusion models → Medical imaging and segmentation
- Preemptive Detection and Steering of LLM Misalignment via Latent ReachabilityLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
- Shortcut Flow Matching for Speech Enhancement: Step-Invariant flows via single stage trainingDiffusion models → Audio, speech and music
- LLM Agent Meets Agentic AI: Can LLM Agents Simulate Customers to Evaluate Agentic-AI-based Shopping Assistants?LLM agents and tool use → Social simulation and multi-agent debate
- Chasing the Tail: Effective Rubric-based Reward Modeling for Large Language Model Post-TrainingLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification
- On Code-Induced Reasoning in LLMsLLM reasoning → Reasoning for agents, planning and code
- SlimDiff: Training-Free, Activation-Guided Hands-free Slimming of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Dual-Head Reasoning Distillation: Improving Classifier Accuracy with Train-Time-Only ReasoningLLM reasoning → Prompting and chain-of-thought reasoning +1
- Reasoning-Enhanced Domain-Adaptive Pretraining of Multimodal Large Language Models for Short Video Content GovernanceLLM reasoning → Multimodal reasoning +1
- Learning to Reason with Mixture of TokensLLM reasoning → Reinforcement learning for reasoning
- d2: Improving Reasoning in Diffusion Language Models via Trajectory Likelihood EstimationLLM reasoning → Diffusion reasoning and test-time scaling +1
- Score-based Idempotent Distillation of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Talking Trees: Reasoning-Assisted Induction of Decision Trees for Tabular DataLLM reasoning → Knowledge- and tool-augmented reasoning
- A State-of-the-Art SQL Reasoning Model using RLVRLLM reasoning → Reinforcement learning for reasoning
- VideoJudge: Bootstrapping Enables Scalable Supervision of MLLM-as-a-Judge for Video UnderstandingSynthetic data and self-improvement for LLMs → Self-improving MLLMs and synthetic data
- One Model, Many Morals: Uncovering Cross-Linguistic Misalignments in Computational Moral ReasoningLLM reasoning → Reasoning benchmarks and evaluation
- DyME: Dynamic Multi-Concept Erasure in Diffusion Models with Bi-Level Orthogonal LoRA AdaptationDiffusion models → Robustness, privacy and adversarial aspects
- SciReasoner: Laying the Scientific Reasoning Ground Across DisciplinesLLM reasoning → Knowledge- and tool-augmented reasoning
- RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable RewardsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- VC-Agent: An Interactive Agent for Customized Video Dataset CollectionLLM agents and tool use → Multimodal and embodied agents
- DisCoCLIP: A Distributional Compositional Tensor Network Encoder for Vision-Language UnderstandingMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Bounds of Chain-of-Thought Robustness: Reasoning Steps, Embed Norms, and BeyondLLM reasoning → Prompting and chain-of-thought reasoning
- It's Not You, It's Clipping: A Soft Trust-Region via Probability Smoothing for LLM RLLLM reasoning → Reinforcement learning for reasoning
- MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open ResourcesLLM reasoning → Multimodal reasoning
- Rethinking Explainable Disease Prediction: Synergizing Accuracy and Reliability via Reflective Cognitive ArchitectureLLM reasoning → Clinical and biomedical applications
- Un-Doubling Diffusion: LLM-guided Disambiguation of Homonym DuplicationDiffusion models → Image generation, text-to-image and editing
- Semantic Edge-Cloud Communication for Real-Time Urban Traffic Surveillance with ViT and LLMs over Mobile NetworksMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
- Hallucination as an Upper Bound: A New Perspective on Text-to-Image EvaluationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
- Instruction-tuned Self-Questioning Framework for Multimodal ReasoningLLM reasoning → Multimodal reasoning
- Federated Flow MatchingDiffusion models → Robustness, privacy and adversarial aspects
- Decipher-MR: A Vision-Language Foundation Model for 3D MRI RepresentationsMultimodal LLMs / vision-language models → Medical vision-language models
- Learning to Look: Cognitive Attention Alignment with Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- RetoVLA: Reusing Register Tokens for Spatial Reasoning in Vision-Language-Action ModelsLLM reasoning → Spatial and embodied reasoning +1
- Tree Search for LLM Agent Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents
- SlideMamba: Entropy-Based Adaptive Fusion of GNN and Mamba for Enhanced Representation Learning in Digital PathologyState-space sequence models (S4, Mamba) → Mamba for medical image analysis
- Query-Centric Graph Retrieval Augmented GenerationLLM reasoning → Knowledge- and tool-augmented reasoning +1
- AbideGym: Turning Static RL Worlds into Adaptive ChallengesDeep reinforcement learning methods → Deep RL algorithms and representations
- What Do LLM Agents Do When Left Alone? Evidence of Spontaneous Meta-Cognitive PatternsLLM agents and tool use → General LLM agent frameworks and benchmarks
- SGMem: Sentence Graph Memory for Long-Term Conversational AgentsLLM agents and tool use → Agent memory systems
- CLaw: Benchmarking Chinese Legal Knowledge in Large Language Models - A Fine-grained Corpus and Reasoning AnalysisLLM reasoning → Reasoning for agents, planning and code
- A Fano-Style Accuracy Upper Bound for LLM Single-Pass Reasoning in Multi-Hop QALLM reasoning → Knowledge- and tool-augmented reasoning
- Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning +1
- Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context DiscrepancySynthetic data and self-improvement for LLMs → Model collapse from synthetic data
- Less Precise Can Be More Reliable: A Systematic Evaluation of Quantization's Impact on VLMs Beyond AccuracyMultimodal LLMs / vision-language models → Visual token pruning and efficiency
- Inverse Reinforcement Learning with Just Classification and a Few RegressionsOffline RL and imitation learning from data → Inverse reinforcement learning +1
- Fine-Tuning LLMs to Analyze Multiple Dimensions of Code Review: A Maximum Entropy Regulated Long Chain-of-Thought ApproachLLM reasoning → Reasoning for agents, planning and code
- A Unified Framework for Diffusion Model Unlearning with f-DivergenceDiffusion models → Robustness, privacy and adversarial aspects +1
- Mixture of Thoughts: Learning to Aggregate What Experts Think, Not Just What They SayLLM reasoning → Test-time compute and efficient thinking
- Fast segmentation of watermarked texts from large language models through an epidemic change-point frameworkLLM safety and security → Watermarking generated content and models
- GRPO is Secretly a Process Reward ModelLLM reasoning → Reinforcement learning for reasoning +1
- ToMPO: Training LLM Strategic Decision Making from a Multi-Agent PerspectiveLLM agents and tool use → Reinforcement learning for LLM agents
- EvoMail: Self-Evolving Cognitive Agents for Adaptive Spam and Phishing Email DefenseLLM agents and tool use → Agent threats, guardrails and governance +1
- RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMsLLM reasoning → Reinforcement learning for reasoning
- Teaching RL Agents to Act Better: VLM as Action Advisor for Online Reinforcement LearningVision-language-action models → Reinforcement learning and post-training +1
- Expanding Reasoning Potential in Foundation Model by Learning Diverse Chains of Thought PatternsLLM reasoning → Prompting and chain-of-thought reasoning +1
- Rich State Observations Empower Reinforcement Learning to Surpass PID: A Drone Ball Balancing StudyDeep reinforcement learning methods → RL for robot navigation and UAV control
- MOSS-ChatV: Reinforcement Learning with Process Reasoning Reward for Video Temporal ReasoningLLM reasoning → Multimodal reasoning +2
- Cross-Modal Instructions for Robot Motion GenerationDeep reinforcement learning methods → RL for robot locomotion and manipulation
- Mammo-CLIP Dissect: A Framework for Analysing Mammography Concepts in Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
- VideoChat-R1.5: Visual Test-Time Scaling to Reinforce Multimodal Reasoning by Iterative PerceptionLLM reasoning → Multimodal reasoning +1
- ScaleDiff: Scaling Difficult Problems for Advanced Mathematical ReasoningLLM reasoning → Mathematical reasoning
All 491
- SPREAD: Sampling-based Pareto front Refinement via Efficient Adaptive DiffusionDiffusion models → Diffusion foundations and sampling
- PMark: Towards Robust and Distortion-free Semantic-level Watermarking with Channel ConstraintsLLM safety and security → Watermarking generated content and models
- Reasoning or Rambling? Exploring the Effect of Thinking on Agent PersuasionLLM reasoning → Reasoning for agents, planning and code +1
- GeoRef: Referring Expressions in Geometry via Task Formulation, Synthetic Supervision, and Reinforced MLLM-based SolutionsLLM reasoning → Spatial and embodied reasoning
- MPC-based Deep Reinforcement Learning Method for Space Robotic Control with Fuel Sloshing MitigationDeep reinforcement learning methods → RL for robot navigation and UAV control
- CLAUSE: Agentic Neuro-Symbolic Knowledge Graph Reasoning via Dynamic Learnable Context EngineeringLLM agents and tool use → Web, search, and research agents
- SupCLAP: Controlling Optimization Trajectory Drift in Audio-Text Contrastive Learning with Support Vector RegularizationMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
- FORCE: Transferable Visual Jailbreaking Attacks via Feature Over-Reliance CorrEctionMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
- SciTrek: Evaluating and Improving Long-Context Numerical Reasoning over Scientific ArticlesLLM reasoning → Knowledge- and tool-augmented reasoning
- KeyWorld: Key Frame Reasoning Enables Effective and Efficient World ModelsWorld models → Embodied and robot world models
- Actor-Critic without ActorDeep reinforcement learning methods → RL theory and sample complexity
- Predicting LLM Reasoning Performance with Small Proxy ModelLLM reasoning → Reasoning benchmarks and evaluation
- Automatic Red Teaming LLM-based Agents with Model Context Protocol ToolsLLM agents and tool use → Agent threats, guardrails and governance +1
- RollPacker: Mitigating Long-Tail Rollouts for Fast, Synchronous RL Post-TrainingLLM reasoning → Reinforcement learning for reasoning
- A Single Neuron Works: Precise Concept Erasure in Text-to-Image Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +2
- CORE: Full-Path Evaluation of LLM Agents Beyond Final StateLLM agents and tool use → General LLM agent frameworks and benchmarks
- Binary Autoencoder for Mechanistic Interpretability of Large Language ModelsMechanistic interpretability → SAE features and their applications
- Rejuvenating Cross-Entropy Loss in Knowledge Distillation for Recommender SystemsKnowledge distillation → Distillation for recommender systems
- SiNGER: A Clearer Voice Distills Vision Transformers FurtherKnowledge distillation → General knowledge distillation methods
- CLUE: Conflict-guided Localization for LLM Unlearning FrameworkLLM safety and security → Machine unlearning +1
- Tool Calling for Arabic LLMs: Data Strategies and Instruction TuningLLM agents and tool use → Tool learning and function calling
- Flow Matching in the Low-Noise Regime: Pathologies and a Contrastive RemedyDiffusion models → Flow matching, time series and science
- Autoregressive End-to-End Planning with Time-Invariant Spatial Alignment and Multi-Objective Policy RefinementLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- GALAX: Graph-Augmented Language Model for Explainable Reinforcement-Guided Subgraph Reasoning in Precision MedicineLLM reasoning → Clinical and biomedical applications +1
- Conditionally Whitened Generative Models for Probabilistic Time Series ForecastingDiffusion models → Flow matching, time series and science
- SimDiff: Simulator-constrained Diffusion Model for Physically Plausible Motion GenerationDiffusion models → Video generation
- RLCracker: Evaluating the Worst-Case Vulnerability of LLM Watermarks with Adaptive RL AttacksLLM safety and security → Watermarking generated content and models
- SwinMamba: A hybrid local-global mamba framework for enhancing semantic segmentation of remotely sensed imagesState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
- DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful ReasoningLLM reasoning → Multimodal reasoning +1
- Learning to Summarize by Learning to Quiz: Adversarial Agentic Collaboration for Long Document SummarizationLLM agents and tool use → General LLM agent frameworks and benchmarks
- Deterministic Discrete DenoisingDiffusion models → Diffusion foundations and sampling
- AIBA: Attention-based Instrument Band Alignment for Text-to-Audio DiffusionDiffusion models → Audio, speech and music
- Nuclear Diffusion Models for Low-Rank Background Suppression in VideosDiffusion models → Medical imaging and segmentation
- Model-Based Reinforcement Learning under Random Observation DelaysDeep reinforcement learning methods → Deep RL algorithms and representations
- StyleBench: Evaluating thinking styles in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
- On the Robustness of Answer Formats in Medical Reasoning ModelsLLM reasoning → Clinical and biomedical applications
- GIFT: Guided Importance-Aware Fine-Tuning for Diffusion Language ModelsDiffusion models → Discrete and text diffusion
- Concise and Sufficient Sub-Sentence Citations for Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
- ArchGPT: Understanding the World's Architectures with Large Multimodal ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Punching Above Precision: Small Quantized Model Distillation with Learnable RegularizerKnowledge distillation → Knowledge distillation for LLMs
- Causal Time Series Generation via Diffusion ModelsDiffusion models → Flow matching, time series and science
- MTRDrive: Memory-Tool Synergistic Reasoning for Robust Autonomous Driving in Corner CasesLLM reasoning → Chain-of-thought reasoning for driving +2
- CaTS-Bench: Can Language Models Describe Time Series?LLM reasoning → Time series reasoning
- T2I-Diff: fMRI Signal Generation via Time-Frequency Image Transform and Classifier-Free Denoising Diffusion ModelsDiffusion models → Medical imaging and segmentation
- Enrich-on-Graph: Query-Graph Alignment for Complex Reasoning with LLM EnrichingLLM reasoning → Knowledge- and tool-augmented reasoning
- LogReasoner: Empowering LLMs with Expert-like Coarse-to-Fine Reasoning for Automated Log AnalysisLLM reasoning → Reasoning for agents, planning and code
- DAC-LoRA: Dynamic Adversarial Curriculum for Efficient and Robust Few-Shot AdaptationMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
- Towards Atoms of Large Language ModelsMechanistic interpretability → SAE features and their applications
- CusEnhancer: A Zero-Shot Scene and Controllability Enhancement Method for Photo Customization via ResInversionDiffusion models → Image generation, text-to-image and editing
- Provenance Analysis of Archaeological Artifacts via Multimodal RAG SystemsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
- Measuring LLM Sensitivity in Transformer-based Tabular Data SynthesisSynthetic data and self-improvement for LLMs → Privacy-preserving tabular data synthesis
- Leveraging Temporally Extended Behavior Sharing for Multi-task Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
- FreeInsert: Personalized Object Insertion with Geometric and Style ControlDiffusion models → 3D, point cloud and scene generation
- Meta-Memory: Retrieving and Integrating Semantic-Spatial Memories for Robot Spatial ReasoningLLM reasoning → Spatial and embodied reasoning
- Seeing Through Words, Speaking Through Pixels: Deep Representational Alignment Between Vision and Language ModelsLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
- Parallel Thinking, Sequential Answering: Bridging NAR and AR for Efficient ReasoningLLM reasoning → Test-time compute and efficient thinking
- Imagining Design Workflows in Agentic AI FuturesLLM agents and tool use → General LLM agent frameworks and benchmarks
- Robust, Observable, and Evolvable Agentic Systems Engineering: A Principled Framework Validated via the Fairy GUI AgentLLM agents and tool use → General LLM agent frameworks and benchmarks
- RobotDancing: Residual-Action Reinforcement Learning Enables Robust Long-Horizon Humanoid Motion TrackingDeep reinforcement learning methods → RL for robot locomotion and manipulation
- CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning +1
- An Automated Retrieval-Augmented Generation LLaMA-4 109B-based System for Evaluating Radiotherapy Treatment PlansRetrieval-augmented generation → Medical and biomedical RAG
- Building Information Models to Robot-Ready Site Digital Twins (BIM2RDT): An Agentic AI Safety-First FrameworkLLM agents and tool use → Multimodal and embodied agents
- RuN: Residual Policy for Natural Humanoid LocomotionDeep reinforcement learning methods → RL for robot locomotion and manipulation
- Adaptive Cybersecurity Architecture for Digital Product Ecosystems Using Agentic AILLM agents and tool use → Agent threats, guardrails and governance
- Recov-Vision: Linking Street View Imagery and Vision-Language Models for Post-Disaster RecoveryMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
- Beyond Chat: a Framework for LLMs as Human-Centered Support Systems
- Joint Active RIS Configuration and User Power Control for Localization: A Neuroevolution-Based Approach
- Towards Multimodal Active Learning: Efficient Learning with Limited Paired Data
- StructPrune: Structured Global Pruning asymptotics with O(√N) GPU Memory
- Frequency-Aware Model Parameter Explorer: A new attribution method for improving explainability
- VFEM: Visual Feature Empowered Multivariate Time Series Forecasting with Cross-Modal Fusion
- Hallucination-Resistant, Domain-Specific Research Assistant with Self-Evaluation and Vector-Grounded Retrieval
- IoT-MCP: Bridging LLMs and IoT Systems Through Model Context Protocol
- Measuring Algorithmic Partisanship via Zero-Shot Classification and Its Implications on Political Discourse
- RJE: A Retrieval-Judgment-Exploration Framework for Efficient Knowledge Graph Question Answering with LLMs
- Kant: An Efficient Unified Scheduling System for Large-Scale AI Clusters
- Simulating Student Success in the Age of GenAI: A Kantian-Axiomatic Perspective
- Learning Inter-Atomic Potentials without Explicit Equivariance
- Fine-tuning of Large Language Models for Domain-Specific Cybersecurity Knowledge
- HAMMER: Hamiltonian Curiosity Augmented Large Language Model Reinforcement
- Quantum est in Libris: Navigating Archives with GenAI, Uncovering Tension Between Preservation and Innovation
- Networks of Causal Abstractions: A Sheaf-theoretic Framework
- Machine Learning for Pattern Detection in Printhead Nozzle Logging
- FedCLF -- Towards Efficient Participant Selection for Federated Learning in Heterogeneous IoV Networks
- Sampling via Gaussian Mixture Approximations
- WDformer: A Wavelet-based Differential Transformer Model for Time Series Forecasting
- Enabling Approximate Joint Sampling in Diffusion LMs
- Automated Formative Feedback for Short-form Writing: An LLM-Driven Approach and Adoption Analysis
- Rebuild AC Power Flow Models with Graph Attention Networks
- Multi-Modal Sentiment Analysis with Dynamic Attention Fusion
- A Meta-Analysis of LLM Effects on Students across Qualification, Socialisation, and Subjectification
- PQFed: A Privacy-Preserving Quality-Controlled Federated Learning Framework
- Downscaling human mobility data based on demographic socioeconomic and commuting characteristics using interpretable machine learning methods
- Exact Subgraph Isomorphism Network with Mixed L0,2 Norm Constraint for Predictive Graph Mining
- GRAB: A Risk Taxonomy--Grounded Benchmark for Unsupervised Topic Discovery in Financial Disclosures
- MS-YOLO: Infrared Object Detection for Edge Deployment via MobileNetV4 and SlideLoss
- Wav2Arrest 2.0: Long-Horizon Cardiac Arrest Prediction with Time-to-Event Modeling, Identity-Invariance, and Pseudo-Lab Alignment
- ReviewScore: Misinformed Peer Review Detection with Large Language Models
- Prophecy: Inferring Formal Properties from Neuron Activations
- HuLA: Prosody-Aware Anti-Spoofing with Multi-Task Learning for Expressive and Emotional Synthetic Speech
- Scalable Second-order Riemannian Optimization for K-means Clustering
- QueryGym: Step-by-Step Interaction with Relational Databases
- SlotFM: A Motion Foundation Model with Slot Attention for Diverse Downstream Tasks
- Neuroprobe: Evaluating Intracranial Brain Responses to Naturalistic Stimuli
- MORPH: PDE Foundation Models with Arbitrary Data Modality
- DIM: Enforcing Domain-Informed Monotonicity in Deep Neural Networks
- Automating Sensor Characterization with Bayesian Optimization
- A Systematic Review of Conformal Inference Procedures for Treatment Effect Estimation: Methods and Challenges
- Differentiable Structure Learning and Causal Discovery for General Binary Data
- Limitations on Accurate, Trusted, Human-level Reasoning
- A regret minimization approach to fixed-point iterations
- Can AI Perceive Physical Danger and Intervene?
- Understanding and Enhancing Mask-Based Pretraining towards Universal Representations
- Automated Machine Learning Pipeline: Large Language Models-Assisted Automated Dataset Generation for Training Machine-Learned Interatomic Potentials
- BoHA: Blockwise Hadamard Product Adaptation for Parameter-Efficient Fine-Tuning
- Semantic F1 Scores: Fair Evaluation Under Fuzzy Class Boundaries
- Towards Transparent AI: A Survey on Explainable Language Models
- Quokka: Accelerating Program Verification with LLMs via Invariant Synthesis
- Comparing and Integrating Different Notions of Representational Correspondence in Neural Systems
- HIP: Hessian Interatomic Potentials without derivatives
- PreLoRA: Hybrid Pre-training of Vision Transformers with Full Training and Low-Rank Adapters
- LANCE: Low Rank Activation Compression for Efficient On-Device Continual Learning
- Effective continuous equations for adaptive SGD: a stochastic analysis view
- Multi-Objective Reinforcement Learning for Large Language Model Optimization: Visionary Perspective
- Causal Abstraction Inference under Lossy Representations
- Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projection
- GenUQ: Predictive Uncertainty Estimates via Generative Hyper-Networks
- Automated and Interpretable Survival Analysis from Multimodal Data
- AUDDT: A Unified Benchmark Toolkit for Audio and Speech Deepfake Detectors
- Temporal vs. Spatial: Comparing DINOv3 and V-JEPA2 Feature Representations for Video Action Analysis
- What Happens Next? Anticipating Future Motion by Generating Point Trajectories
- IndiSeek learns information-guided disentangled representations
- Leveraging Big Data Frameworks for Spam Detection in Amazon Reviews
- Interpretable time series analysis with Gumbel dynamics
- "Be My Cheese?": Assessing Cultural Nuance in Multilingual LLM Translations
- Enhancing Contrastive Learning for Geolocalization by Discovering Hard Negatives on Semivariograms
- General Pruning Criteria for Fast SBL
- EEG-Based Consumer Behaviour Prediction: An Exploration from Classical Machine Learning to Graph Neural Networks
- Comparative Personalization for Multi-document Summarization
- Unsupervised Defect Detection for Surgical Instruments
- Generation-Time vs. Post-hoc Citation: A Holistic Evaluation of LLM Attribution
- Domain-Aware Speaker Diarization On African-Accented English
- C-QUERI: Congressional Questions, Exchanges, and Responses in Institutions Dataset
- Machine Learning. The Science of Selection under Uncertainty
- Evidence for Limited Metacognition in LLMs
- Psychological and behavioural responses in human-agent vs. human-human interactions: a systematic review and meta-analysis
- Agribot: agriculture-specific question answer system
- A circuit for predicting hierarchical structure in-context in Large Language Models
- Expert-guided Clinical Text Augmentation via Query-Based Model Collaboration
- TRiCo: Triadic Game-Theoretic Co-Training for Robust Semi-Supervised Learning
- Provable Scaling Laws of Feature Emergence from Learning Dynamics of Grokking
- Knowing When to Defer: Selective Prediction for Responsible Knowledge Tracing
- DistillKac: Few-Step Image Generation via Damped Wave Equations
- Contrastive Mutual Information Learning: Toward Robust Representations without Positive-Pair Augmentations
- New Algorithmic Directions in Optimal Transport and Applications for Product Spaces
- Functional Encryption in Secure Neural Network Training: Data Leakage and Practical Mitigations
- Context-Aware Hybrid Routing in Bluetooth Mesh Networks Using Multi-Model Machine Learning and AODV Fallback
- GraphPFN: A Prior-Data Fitted Graph Foundation Model
- Neural Operators for Mathematical Modeling of Transient Fluid Flow in Subsurface Reservoir Systems
- High-probability zeroth-order online convex optimisation beyond Euclidean geometry
- Filtering with Confidence: When Data Augmentation Meets Conformal Prediction
- VISION: Prompting Ocean Vertical Velocity Reconstruction from Incomplete Observations
- Are Hallucinations Bad Estimations?
- Gender Stereotypes in Professional Roles Among Saudis: An Analytical Study of AI-Generated Images Using Language Models
- Residual Vector Quantization For Communication-Efficient Multi-Agent Perception
- Enhanced Generative Machine Listener
- Diagnosing the Performance Trade-off in Moral Alignment: A Case Study on Gender Stereotypes
- LLM-Based Support for Diabetes Diagnosis: Opportunities, Scenarios, and Challenges with GPT-5
- ARTI-6: Towards Six-dimensional Articulatory Speech Encoding
- Forecasting Seismic Waveforms: A Deep Learning Approach for Einstein Telescope
- Foundation models for high-energy physics
- PhenoMoler: Phenotype-Guided Molecular Optimization via Chemistry Large Language Model
- Near-Optimal Experiment Design in Linear non-Gaussian Cyclic Models
- QuadGPT: Native Quadrilateral Mesh Generation with Autoregressive Models
- Overview of ExpertLifeCLEF 2018: how far automated identification systems are from the best experts?
- Null-Space Filtering for Data-Free Continual Model Merging: Preserving Stability, Promoting Plasticity
- SD3.5-Flash: Distribution-Guided Distillation of Generative Flows
- Interactive Recommendation Agent with Active User Commands
- SAGE: A Realistic Benchmark for Semantic Understanding
- NewtonGen: Physics-Consistent and Controllable Text-to-Video Generation via Neural Newtonian Dynamics
- Sycophancy Is Not One Thing: Causal Separation of Sycophantic Behaviors in LLMs
- Quantized Visual Geometry Grounded Transformer
- No Prior, No Leakage: Revisiting Reconstruction Attacks in Trained Neural Networks
- UPDESH: Synthesizing Grounded Instruction Tuning Data for 13 Indic Languages
- Optimal Robust Recourse with Lp-Bounded Model Change
- Maxout Polytopes
- Taxonomy-aware Dynamic Motion Generation on Hyperbolic Manifolds
- Does FLUX Already Know How to Perform Physically Plausible Image Composition?
- Concertina: Data-Centric Adaptive Pipeline Parallelism for Efficient Heterogeneous Long-Context LLM Training
- A Sentinel-3 foundation model for ocean colour
- SuperOffload: Unleashing the Power of Large-Scale LLM Training on Superchips
- LLMTrace: A Corpus for Classification and Fine-Grained Localization of AI-Written Text
- Task-Dependent Evaluation of LLM Output Homogenization: A Taxonomy-Guided Framework
- MedVSR: Medical Video Super-Resolution with Cross State-Space Propagation
- Towards Geometry-Grounded Dense Semantic Matching with VGGT Priors
- Every Subtlety Counts: Fine-grained Person Independence Micro-Action Recognition via Distributionally Robust Optimization
- A Causality-Aware Spatiotemporal Model for Multi-Region and Multi-Pollutant Air Quality Forecasting
- humancompatible.train: Implementing Optimization Algorithms for Stochastically-Constrained Stochastic Optimization Problems
- Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets
- Explaining Fine Tuned LLMs via Counterfactuals A Knowledge Graph Driven Framework
- Response to Promises and Pitfalls of Deep Kernel Learning
- Evaluating the Evaluators: Metrics for Compositional Text-to-Image Generation
- Sigma: Semantically Informative Pre-training for Skeleton-based Sign Language Understanding
- Go With The Flow: Churn-Tolerant Decentralized Training of Large Language Models
- Evading Overlapping Community Detection via Proxy Node Injection
- Learning Conformal Explainers for Image Classifiers
- From Physics to Machine Learning and Back: Part II - Learning and Observational Bias in PHM
- Data-driven Neural Networks for Windkessel Parameter Calibration
- TABLET: A Large-Scale Dataset for Robust Visual Table Understanding
- Differential-Integral Neural Operator for Long-Term Turbulence Forecasting
- GEP: A GCG-Based method for extracting personally identifiable information from chatbots built on small language models
- Human-like Navigation in a World Built for Humans
- Adoption, usability and perceived clinical value of a UK AI clinical reference platform (iatroX): a mixed-methods formative evaluation of real-world usage and a 1,223-respondent user survey
- Closed-form ℓr norm scaling with data for overparameterized linear regression and diagonal linear networks under ℓp bias
- IntSR: An Integrated Generative Framework for Search and Recommendation
- Who's Laughing Now? An Overview of Computational Humour Generation and Explanation
- Breaking the curse of dimensionality for linear rules: optimal predictors over the ellipsoid
- Distributed Specialization: Rare-Token Neurons in Large Language Models
- DATS: Distance-Aware Temperature Scaling for Calibrated Class-Incremental Learning
- Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in Language Models
- WAVECLIP: Wavelet Tokenization for Adaptive-Resolution CLIP
- Retrieval over Classification: Integrating Relation Semantics for Multimodal Relation Extraction
- CAD-Tokenizer: Towards Text-based CAD Prototyping via Modality-Specific Tokenization
- LAVA: Explainability for Unsupervised Latent Embeddings
- Emerging Paradigms for Securing Federated Learning Systems
- UniSS: Unified Expressive Speech-to-Speech Translation with Your Voice
- Automotive-ENV: Benchmarking Multimodal Agents in Vehicle Interface Systems
- AutoIntent: AutoML for Text Classification
- Embodied Representation Alignment with Mirror Neurons
- The Unwinnable Arms Race of AI Image Detection
- Sparse Representations Improve Adversarial Robustness of Neural Network Classifiers
- Acoustic-based Gender Differentiation in Speech-aware Language Models
- Physics Informed Neural Networks for design optimisation of diamond particle detectors for charged particle fast-tracking at high luminosity hadron colliders
- MotionFlow:Learning Implicit Motion Flow for Complex Camera Trajectory Control in Video Generation
- TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them
- CHARM: Control-point-based 3D Anime Hairstyle Auto-Regressive Modeling
- VoiceBBQ: Investigating Effect of Content and Acoustics in Social Bias of Spoken Language Model
- BESPOKE: Benchmark for Search-Augmented Large Language Model Personalization via Diagnostic Feedback
- PerHalluEval: Persian Hallucination Evaluation Benchmark for Large Language Models
- GraphUniverse: Synthetic Graph Generation for Evaluating Inductive Generalization
- Best-of-∞ -- Asymptotic Performance of Test-Time LLM Ensembling
- Are Modern Speech Enhancement Systems Vulnerable to Adversarial Attacks?
- UniTransfer: Video Concept Transfer via Progressive Spatial and Timestep Decomposition
- Vision Transformers: the threat of realistic adversarial patches
- TyphoonMLA: A Mixed Naive-Absorb MLA Kernel For Shared Prefix
- InsideOut: Measuring and Mitigating Insider-Outsider Bias in Interview Script Generation
- SoM-1K: A Thousand-Problem Benchmark Dataset for Strength of Materials
- Communication Bias in Large Language Models: A Regulatory Perspective
- Recon-Act: A Self-Evolving Multi-Agent Browser-Use System via Web Reconnaissance, Tool Generation, and Task Execution
- EnGraf-Net: Multiple Granularity Branch Network with Fine-Coarse Graft Grained for Classification Task
- Structure-Attribute Transformations with Markov Chain Boost Graph Domain Adaptation
- Stratify or Die: Rethinking Data Splits in Image Segmentation
- Background Prompt for Few-Shot Out-of-Distribution Detection
- When Instructions Multiply: Measuring and Estimating LLM Capabilities of Multiple Instructions Following
- Physics of Learning: A Lagrangian perspective to different learning paradigms
- Reinforcement Learning Fine-Tuning Enhances Activation Intensity and Diversity in the Internal Circuitry of LLMs
- Measuring Combinatorial Creativity in Large Language Models and Humans
- LayerNorm Induces Recency Bias in Transformer Decoders
- Generative AI for FFRDCs
- OmniPlantSeg: Species Agnostic 3D Point Cloud Organ Segmentation for High-Resolution Plant Phenotyping Across Modalities
- Efficient Ensemble Conditional Independence Test Framework for Causal Discovery
- RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs?
- The Use of the Simplex Architecture to Enhance Safety in Deep-Learning-Powered Autonomous Systems
- Mechanism of Task-oriented Information Removal in In-context Learning
- Bridging the phenotype-target gap for molecular generation via multi-objective reinforcement learning
- Marching Neurons: Accurate Surface Extraction for Neural Implicit Shapes
- AnywhereVLA: Language-Conditioned Exploration and Mobile Manipulation
- Multi-Agent Inverted Transformer for Flight Trajectory Prediction
- Lossless Compression: A New Benchmark for Time Series Model Evaluation
- Feature Augmentation of GNNs for ILPs: Local Uniqueness Suffices
- Learning the Inverse Temperature of Ising Models under Hard Constraints using One Sample
- Fast-SEnSeI: Lightweight Sensor-Independent Cloud Masking for On-board Multispectral Sensors
- AOT*: Efficient Synthesis Planning via LLM-Empowered AND-OR Tree Search
- Empirical PAC-Bayes Bounds for Markov Chains
- Analysis of instruction-based LLMs' capabilities to score and judge text-input problems in an academic setting
- Toward Robust and Efficient ML-Based GPU Caching for Modern Inference
- FracAug: Fractional Augmentation boost Graph-level Anomaly Detection under Limited Supervision
- An Adaptor for Triggering Semi-Supervised Learning to Out-of-Box Serve Deep Image Clustering
- Knowledgeable Language Models as Black-Box Optimizers for Personalized Medicine
- Dual-Path Phishing Detection: Integrating Transformer-Based NLP with Structural URL Analysis
- i-LAVA: Insights on Low Latency Voice-2-Voice Architecture for Agents
- Alignment Unlocks Complementarity: A Framework for Multiview Circuit Representation Learning
- Unlocking Financial Insights: An advanced Multimodal Summarization with Multimodal Output Framework for Financial Advisory Videos
- Beyond Stars: Bridging the Gap Between Ratings and Review Sentiment with LLM
- Decoupled-Value Attention for Prior-Data Fitted Networks: GP Inference for Physical Equations
- A Real-Time On-Device Defect Detection Framework for Laser Power-Meter Sensors via Unsupervised Learning
- CTI Dataset Construction from Telegram
- Why Attention Fails: The Degeneration of Transformers into MLPs in Time Series Forecasting
- Decoding the Surgical Scene: A Scoping Review of Scene Graphs in Surgery
- Unlocking Noise-Resistant Vision: Key Architectural Secrets for Robust Models
- GenFacts-Generative Counterfactual Explanations for Multi-Variate Time Series
- Reverse Fa`a di Bruno's Formula for Cartesian Reverse Differential Categories
- Energy saving in off-road vehicles using leakage compensation technique
- Revisiting Data Challenges of Computational Pathology: A Pack-based Multiple Instance Learning Training Framework
- Cross-Linguistic Analysis of Memory Load in Sentence Comprehension: Linear Distance and Structural Density
- Deep Learning for Crime Forecasting: The Role of Mobility at Fine-grained Spatiotemporal Scales
- LogitTrace: Detecting Benchmark Contamination via Layerwise Logit Trajectories
- Distant Object Localisation from Noisy Image Segmentation Sequences
- FSMODNet: A Closer Look at Few-Shot Detection in Multispectral Data
- Concepts in Motion: Temporal Concept Bottleneck Model for Interpretable Video Classification
- FerretNet: Efficient Synthetic Image Detection via Local Pixel Dependencies
- Improving Early Sepsis Onset Prediction Through Federated Learning
- Integrating Object Interaction Self-Attention and GAN-Based Debiasing for Visual Question Answering
- RecIS: Sparse to Dense, A Unified Training Framework for Recommendation Models
- On Theoretical Interpretations of Concept-Based In-Context Learning
- The Unanticipated Asymmetry Between Perceptual Optimization and Assessment
- Distribution-Controlled Client Selection to Improve Federated Learning Strategies
- SCRA-VQA: Summarized Caption-Rerank for Augmented Large Language Models in Visual Question Answering
- Plant identification in an open-world (LifeCLEF 2016)
- Federated Markov Imputation: Privacy-Preserving Temporal Imputation in Multi-Centric ICU Environments
- SD-RetinaNet: Topologically Constrained Semi-Supervised Retinal Lesion and Layer Segmentation in OCT
- TasselNetV4: A vision foundation model for cross-scene, cross-scale, and cross-species plant counting
- Plant identification based on noisy web data: the amazing performance of deep learning (LifeCLEF 2017)
- FHRFormer: A Self-supervised Transformer Approach for Fetal Heart Rate Inpainting and Forecasting
- Poisoning Prompt-Guided Sampling in Video Large Language Models
- Actively Learning Halfspaces without Synthetic Data
- Robust Multi-Omics Integration from Incomplete Modalities Significantly Improves Prediction of Alzheimer's Disease
- ImaginationPolicy: Towards Generalizable, Precise and Reliable End-to-End Policy for Robotic Manipulation
- Shaping Initial State Prevents Modality Competition in Multi-modal Fusion: A Two-stage Scheduling Framework via Fast Partial Information Decomposition
- Zero-Shot Privacy-Aware Text Rewriting via Iterative Tree Search
- Verification Limits Code LLM Training
- Security-aware Semantic-driven ISAC via Paired Adversarial Residual Networks
- Trustworthy Semantic Communication for Vehicular Networks: Challenges and Solutions
- Explaining Grokking and Information Bottleneck through Neural Collapse Emergence
- ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail Prediction
- Distilling Many-Shot In-Context Learning into a Cheat Sheet
- Even More Kawaii than Real-Person-Driven VTubers? Understanding How Viewers Perceive AI-Driven VTubers
- Revolutionizing Precise Low Back Pain Diagnosis via Contrastive Learning
- Leveraging What's Overfixed: Post-Correction via LLM Grammatical Error Overcorrection
- Federated Domain Generalization with Domain-specific Soft Prompts Generation
- Few-Shot and Training-Free Review Generation via Conversational Prompting
- FERD: Fairness-Enhanced Data-Free Robustness Distillation
- Aligning Inductive Bias for Data-Efficient Generalization in State Space Models
- Real-Time Object Detection Meets DINOv3
- LiLAW: Lightweight Learnable Adaptive Weighting to Learn Sample Difficulty & Improve Noisy Training
- Dual-supervised Asymmetric Co-training for Semi-supervised Medical Domain Generalization
- IConv: Focusing on Local Variation with Channel Independent Convolution for Multivariate Time Series Forecasting
- Sig2Model: A Boosting-Driven Model for Updatable Learned Indexes
- CompressAI-Vision: Open-source software to evaluate compression methods for computer vision tasks
- Extrapolating Phase-Field Simulations in Space and Time with Purely Convolutional Architectures
- Identifying Group Anchors in Real-World Group Interactions Under Label Scarcity
- SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs
- MASt3R-Fusion: Integrating Feed-Forward Visual Model with IMU, GNSS for High-Functionality SLAM
- RAPTOR-GEN: RApid PosTeriOR GENerator for Bayesian Learning in Biomanufacturing
- Confidence-guided Refinement Reasoning for Zero-shot Question Answering
- AI-Enabled Crater-Based Navigation for Lunar Mapping
- Neptune-X: Active X-to-Maritime Generation for Universal Maritime Object Detection
- Real-Time System for Audio-Visual Target Speech Enhancement
- Decision-Driven Semantic Object Exploration for Legged Robots via Confidence-Calibrated Perception and Topological Subgoal Selection
- The Impact of Audio Watermarking on Audio Anti-Spoofing Countermeasures
- Probability Distribution Collapse: A Critical Bottleneck to Compact Unsupervised Neural Grammar Induction
- PALQO: Physics-informed Model for Accelerating Large-scale Quantum Optimization
- SeamCrafter: Enhancing Mesh Seam Generation for Artist UV Unwrapping via Reinforcement Learning
- Visual Authority and the Rhetoric of Health Misinformation: A Multimodal Analysis of Social Media Videos
- Scaling Laws are Redundancy Laws
- A Genetic Algorithm for Navigating Synthesizable Molecular Spaces
- Beyond the Individual: Introducing Group Intention Forecasting with SHOT Dataset
- Cryptographic Backdoor for Neural Networks: Boon and Bane
- ArtUV: Artist-style UV Unwrapping
- MI-Fuse: Label Fusion for Unsupervised Domain Adaptation with Closed-Source Large-Audio Language Model
- Joint Flow Trajectory Optimization For Feasible Robot Motion Generation from Video Demonstrations
- Incorporating LLM Embeddings for Variation Across the Human Genome
- DENet: Dual-Path Edge Network with Global-Local Attention for Infrared Small Target Detection
- Overcoming Black-box Attack Inefficiency with Hybrid and Dynamic Select Algorithms
- Learning to Align Molecules and Proteins: A Geometry-Aware Approach to Binding Affinity
- RedHerring Attack: Testing the Reliability of Attack Detection
- RAM-NAS: Resource-aware Multiobjective Neural Architecture Search Method for Robot Vision Tasks
- Enhancing Cross-View Geo-Localization Generalization via Global-Local Consistency and Geometric Equivariance
- Implicit Augmentation from Distributional Symmetry in Turbulence Super-Resolution
- Addressing Gradient Misalignment in Data-Augmented Training for Robust Speech Deepfake Detection
- Efficient Construction of Implicit Surface Models From a Single Image for Motion Generation
- Can Federated Learning Safeguard Private Data in LLM Training? Vulnerabilities, Attacks, and Defense Evaluation
- QAMO: Quality-aware Multi-centroid One-class Learning For Speech Deepfake Detection
- Bispectral OT: Dataset Comparison using Symmetry-Aware Optimal Transport
- Stability of In-Context Learning: A Spectral Coverage Perspective
- Equi-RO: A 4D mmWave Radar Odometry via Equivariant Networks
- Human Semantic Representations of Social Interactions from Moving Shapes
- Guiding Application Users via Estimation of Computational Resources for Massively Parallel Chemistry Computations
- Understanding Role Switching in Human-AI Collaboration through Multimodal Behavioral Signals
- Enhancing Molecular Property Prediction with Knowledge from Large Language Models
- Building Tailored Speech Recognizers for Japanese Speaking Assessment
- Accelerate Creation of Product Claims Using Generative AI
- Wonder Wins Ways: Curiosity-Driven Exploration through Multi-Agent Contextual Calibration
- Anticipatory Evaluation of Language Models: Predicting LLM Benchmark Scores from Descriptions
- Investigating Modality Contribution in Audio LLMs for Music
- A Framework for Rapidly Developing and Deploying Protection Against Large Language Model Attacks
- A Hierarchical Variational Graph Fused Lasso for Recovering Relative Rates in Spatial Compositional Data
- Learning Terrain-Specialized Policies for Adaptive Locomotion in Challenging Environments
- Recidivism Prediction, Peer Effect Estimation, and Prediction-Powered Inference with LLM Text Measures
- Design, Implementation and Evaluation of a Novel Programming Language Topic Classification Workflow
- Personalized Federated Dictionary Learning for Modeling Heterogeneity in Multi-site fMRI Data