mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 17 May 2025

254 papers

  1. Pairwise Calibrated Rewards for Pluralistic AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  2. Mutual-Taught for Co-adapting Policy and Reward ModelsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  3. Mixture of Decoding: An Attention-Inspired Adaptive Decoding Strategy to Mitigate Hallucinations in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  4. DO-RAG: A Domain-Specific QA Framework Using Knowledge Graph-Enhanced Retrieval-Augmented GenerationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  5. DraftAttention: Fast Video Diffusion via Low-Resolution Attention GuidanceDiffusion models → Video generation
  6. Data Balancing Strategies: A Systematic Survey of Resampling and Augmentation MethodsDiffusion models → Diffusion foundations and sampling
  7. HALO: Hierarchical Autonomous Logic-Oriented Orchestration for Multi-Agent LLM SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  8. Federated Deep Reinforcement Learning for Privacy-Preserving Robotic-Assisted SurgeryDeep reinforcement learning methods → RL for clinical treatment and surgery
  9. Reasoning Large Language Model Errors Arise from Hallucinating Critical Problem FeaturesLLM reasoning → Reasoning benchmarks and evaluation
  10. LLM-BabyBench: Can Language Models Plan in Worlds They Can Simulate?LLM agents and tool use → General LLM agent frameworks and benchmarks
  11. SAINT: Attention-Based Policies for Discrete Combinatorial Action SpacesDeep reinforcement learning methods → RL with diffusion and flow models
  12. EarthSynth: Generating Informative Earth Observation with Diffusion ModelsDiffusion models → Inverse problems and image restoration
  13. TinyRS-R1: Compact Multimodal Language Model for Remote SensingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  14. LOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text InterpretationMultimodal LLMs / vision-language models → Video understanding with MLLMs
  15. Model Merging in Pre-training of Large Language ModelsMixture-of-experts → MoE large language models
  16. VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement LearningLLM reasoning → Multimodal reasoning +1
  17. Demystifying and Enhancing the Efficiency of Large Language Model Based Search AgentsLLM agents and tool use → Web, search, and research agents
  18. Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard EnhancementLLM safety and security → Jailbreaking
  19. VFRTok: Variable Frame Rates Video Tokenizer with Duration-Proportional Information AssumptionDiffusion models → Video generation
  20. AdaBoN: Adaptive Best-of-N AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  21. Accelerating Diffusion-based Super-Resolution with Dynamic Time-Spatial SamplingDiffusion models → Inverse problems and image restoration
  22. LLM-based Automated Theorem Proving Hinges on Scalable Synthetic Data GenerationSynthetic data and self-improvement for LLMs → Self-play RL for reasoning
  23. GeoMaNO: Geometric Mamba Neural Operator for Partial Differential EquationsState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
  24. Multi-modal Collaborative Optimization and Expansion Network for Event-assisted Single-eye Expression RecognitionMixture-of-experts → Multimodal MoE models +1
  25. SOCIA-nabla: Textual Gradient Meets Multi-Agent Orchestration for Automated Simulator GenerationLLM agents and tool use → Software engineering coding agents
  26. Interactional Fairness in LLM Multi-Agent Systems: An Evaluation FrameworkLLM agents and tool use → Social simulation and multi-agent debate
  27. IQBench: How "Smart'' Are Vision-Language Models? A Study with Human IQ TestsLLM reasoning → Multimodal reasoning +1
  28. Unveiling Knowledge Utilization Mechanisms in LLM-based Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  29. SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited ObservationsDiffusion models → 3D, point cloud and scene generation
  30. TechniqueRAG: Retrieval Augmented Generation for Adversarial Technique Annotation in Cyber Threat Intelligence TextRetrieval-augmented generation → Privacy and security of RAG
  31. Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative VerifierLLM reasoning → Test-time compute and efficient thinking
  32. MARVEL: Multi-Agent RTL Vulnerability Extraction using Large Language ModelsLLM agents and tool use → Agent threats, guardrails and governance
  33. Exploring Criteria of Loss Reweighting to Enhance LLM UnlearningLLM safety and security → Machine unlearning
  34. Let's have a chat with the EU AI ActRetrieval-augmented generation → Legal and financial RAG
  35. LifelongAgentBench: Evaluating LLM Agents as Lifelong LearnersLLM agents and tool use → Agent memory systems
  36. CCD: Continual Consistency Diffusion for Lifelong Generative ModelingDiffusion models → Robustness, privacy and adversarial aspects
  37. ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs' Capability via Chart EditingMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  38. Neuro-Symbolic Query CompilerRetrieval-augmented generation → RAG pipeline design and evaluation
  39. SafeVid: Toward Safety Aligned Video Large Multimodal ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +2
  40. Explaining Intrinsic Moral Self-Correction with Mechanistic InterpretabilityMechanistic interpretability → Probing deception, bias and beliefs
  41. OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive ReasoningVision-language-action models → Reasoning and chain-of-thought in VLA
  42. Arrow: Adaptive Scheduling Mechanisms for Disaggregated LLM Inference ArchitectureEfficient LLM inference and serving → Serving systems and request scheduling
  43. ELITE: Embedding-Less retrieval with Iterative Text ExplorationRetrieval-augmented generation → Generation and context integration
  44. Are Multimodal Large Language Models Ready for Omnidirectional Spatial Reasoning?LLM reasoning → Spatial and embodied reasoning +1
  45. FiGKD: Fine-Grained Knowledge Distillation via High-Frequency Detail TransferKnowledge distillation → General knowledge distillation methods
  46. AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement LearningLLM reasoning → Test-time compute and efficient thinking
  47. RLAP: A Reinforcement Learning Enhanced Adaptive Planning Framework for Multi-step NLP Task SolvingDeep reinforcement learning methods → RL training of language and agent models
  48. Mobile-Bench-v2: A More Realistic and Comprehensive Benchmark for VLM-based Mobile AgentsLLM agents and tool use → GUI and mobile agents
  49. Aux-Think: Exploring Reasoning Strategies for Data-Efficient Vision-Language NavigationLLM reasoning → Spatial and embodied reasoning
  50. J1: Exploring Simple Test-Time Scaling for LLM-as-a-JudgeLLM reasoning → Test-time compute and efficient thinking
  51. PRS-Med: Position Reasoning Segmentation in Medical ImagingLLM reasoning → Clinical and biomedical applications
  52. Learning Pareto-Optimal Rewards from Noisy Preferences: A Framework for Multi-Objective Inverse Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents +3
  53. Q-Policy: Quantum-Enhanced Policy Evaluation for Scalable Reinforcement LearningDeep reinforcement learning methods → Quantum reinforcement learning
  54. Fair-PP: A Synthetic Dataset for Aligning LLM with Personalized Preferences of Social EquityLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment +1
  55. Telco-oRAG: Optimizing Retrieval-augmented Generation for Telecom Queries via Hybrid Retrieval and Neural RoutingRetrieval-augmented generation → RAG robustness and adaptive retrieval
  56. Evaluating the Logical Reasoning Abilities of Large Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  57. Measurement Score-Based Diffusion ModelDiffusion models → Inverse problems and image restoration
  58. MedSG-Bench: A Benchmark for Medical Image Sequences GroundingLLM reasoning → Clinical and biomedical applications +1
  59. VeriReason: Reinforcement Learning with Testbench Feedback for Reasoning-Enhanced Verilog GenerationLLM reasoning → Reasoning for agents, planning and code +1
  60. Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  61. On the Eligibility of LLMs for Counterfactual Reasoning: A Decompositional StudyLLM reasoning → Causal reasoning in LLMs
  62. RVTBench: A Benchmark for Visual Reasoning TasksLLM reasoning → Multimodal reasoning
  63. On Membership Inference Attacks in Knowledge DistillationLLM safety and security → Membership inference attacks +1
  64. SplInterp: Improving our Understanding and Training of Sparse AutoencodersMechanistic interpretability → Sparse autoencoder training and evaluation
  65. Multilingual Collaborative Defense for Large Language ModelsLLM safety and security → Jailbreaking
  66. ToLeaP: Rethinking Development of Tool Learning with Large Language ModelsLLM reasoning → Reasoning for agents, planning and code +1
  67. ARC-AGI-2: A New Challenge for Frontier AI Reasoning SystemsLLM reasoning → Multimodal reasoning
  68. VISTA: Mitigating Semantic Inertia in Video-LLMs via Training-Free Dynamic Chain-of-Thought RoutingLLM reasoning → Multimodal reasoning
  69. Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement LearningLLM reasoning → Test-time compute and efficient thinking
  70. Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted DataDiffusion models → Diffusion foundations and sampling
  71. Latent Veracity Inference for Identifying Errors in Stepwise ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  72. Reinforcing Multi-Turn Reasoning in LLM Agents via Fine-Grained Reward Structure and Credit AssignmentLLM reasoning → Reinforcement learning for reasoning +1
  73. UniMoCo: Unified Modality Completion for Robust Multi-Modal EmbeddingsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  74. SGD-Mix: Enhancing Domain-Specific Image Classification with Label-Preserving Data AugmentationDiffusion models → Image generation, text-to-image and editing
  75. BELLE: A Bi-Level Multi-Agent Reasoning Framework for Multi-Hop Question AnsweringLLM reasoning → Knowledge- and tool-augmented reasoning +1
  76. From Street View to Visual Network: Mapping the Visibility of Urban Landmarks with Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  77. Retrospex: Language Agent Meets Offline Reinforcement Learning CriticLLM reasoning → Reasoning for agents, planning and code +2
  78. Are vision language models robust to uncertain inputs?Multimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  79. Self-Learning Hyperspectral and Multispectral Image Fusion via Adaptive Residual Guided Subspace Diffusion ModelDiffusion models → Inverse problems and image restoration
  80. MedVKAN: Efficient Feature Extraction with Mamba and KAN for Medical Image SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  81. JULI: Jailbreak Large Language Models by Self-IntrospectionLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  82. Improving Coverage in Combined Prediction Sets with Weighted p-valuesMixture-of-experts → MoE theory and gating functions
  83. Self-NPO: Data-Free Diffusion Model Enhancement via Truncated Diffusion Fine-TuningDiffusion models → Diffusion and flow policies for robotics +1
  84. OMAC: A Holistic Optimization Framework for LLM-Based Multi-Agent CollaborationLLM agents and tool use → General LLM agent frameworks and benchmarks
  85. Learning IMU Bias with Diffusion ModelDiffusion models → Diffusion foundations and sampling
  86. Privacy-Preserving AI for Encrypted Medical Imaging: A Framework for Secure Diagnosis and Learning
  87. Confirmation bias: A challenge for scalable oversight
  88. Coupled Entropy: A Goldilocks Generalization for Complex Systems
  89. Llama-Affinity: A Predictive Antibody Antigen Binding Model Integrating Antibody Sequences with Llama3 Backbone Architecture
  90. Rule-based and reinforcement-learning policies for resource allocation in a pediatric echo lab: a simulation study
  91. Dynamic Graph CNN with Jacobi Kolmogorov-Arnold Networks for 3D Classification of Point Sets
  92. dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching
  93. GLProtein: Global-and-Local Structure Aware Protein Representation Learning
  94. Prediction of Bank Credit Ratings using Heterogeneous Topological Graph Neural Networks
  95. Improvement of Optimization using Learning Based Models in Mixed Integer Linear Programming Tasks
  96. Coded Robust Aggregation for Distributed Learning under Byzantine Attacks
  97. Surrogate Interpretable Graph for Random Decision Forests
  98. Equally Critical: Samples, Targets, and Their Mappings in Datasets
  99. Machine Learning-Based Analysis of ECG and PCG Signals for Rheumatic Heart Disease Detection: A Scoping Review (2015-2025)
  100. SALMONN-omni: A Standalone Speech LLM without Codec Injection for Full-duplex Conversation
All 254
  1. Medalyze: Lightweight Medical Report Summarization Application Using FLAN-T5-Large
  2. From Test-taking to Cognitive Scaffolding: A Pedagogical Diagnostic Benchmark for LLMs on English Standardized Tests
  3. TDFormer: A Top-Down Attention-Controlled Spiking Transformer
  4. Curriculum Learning in Genetic Programming Guided Local Search for Large-scale Vehicle Routing Problems
  5. Stochastic Processes with Modified Lognormal Distribution Featuring Flexible Upper Tail
  6. Space evaluation at the starting point of soccer transitions
  7. FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge
  8. A Heuristic Algorithm Based on Beam Search and Iterated Local Search for the Maritime Inventory Routing Problem
  9. Zero-Shot Forecasting Mortality Rates: A Global Study
  10. Beyond Retrieval: Joint Supervision and Multimodal Document Ranking for Textbook Question Answering
  11. Continuous Domain Generalization
  12. LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades
  13. Induction Head Toxicity Mechanistically Explains Repetition Curse in Large Language Models
  14. Learning to Dissipate Energy in Oscillatory State-Space Models
  15. FABLE: A Localized, Targeted Adversarial Attack on Weather Forecasting Models
  16. WaLRUS: Wavelets for Long-range Representation Using SSMs
  17. Emotion Recognition for Low-Resource Turkish: Fine-Tuning BERTurk on TREMO and Testing on Xenophobic Political Discourse
  18. The AI Gap: How Socioeconomic Status Affects Language Technology Interactions
  19. SoftPQ: Robust Instance Segmentation Evaluation via Soft Matching and Tunable Thresholds
  20. Learning to Highlight Audio by Watching Movies
  21. Improving Energy Natural Gradient Descent through Woodbury, Momentum, and Randomization
  22. Causal Machine Learning in IoT-based Engineering Problems: A Tool Comparison in the Case of Household Energy Consumption
  23. Structured Relational Representations
  24. Transformer learns the cross-task prior and regularization for in-context learning
  25. Understanding the Capabilities of Molecular Graph Neural Networks in Materials Science Through Multimodal Learning and Physical Context Encoding
  26. Lightweight Spatio-Temporal Attention Network with Graph Embedding and Rotational Position Encoding for Traffic Forecasting
  27. Towards Sustainability in 6G Network Slicing with Energy-Saving and Optimization Methods
  28. Keypoints as Dynamic Centroids for Unified Human Pose and Segmentation
  29. Metric Graph Kernels via the Tropical Torelli Map
  30. Back to Square Roots: An Optimal Bound on the Matrix Factorization Error for Multi-Epoch Differentially Private SGD
  31. HISTAI: An Open-Source, Large-Scale Whole Slide Image Dataset for Computational Pathology
  32. T-Rex: Fitting a Robust Factor Model via Expectation-Maximization
  33. A Multi-Task Benchmark for Abusive Language Detection in Low-Resource Settings
  34. Behind the Screens: Uncovering Bias in AI-Driven Video Interview Assessments Using Counterfactuals
  35. Learning Probabilistic Temporal Logic Specifications for Stochastic Systems
  36. Improving Fairness in LLMs Through Testing-Time Adversaries
  37. Proximal optimal transport divergences
  38. When Bias Meets Trainability: Connecting Theories of Initialization
  39. Attribution Projection Calculus: A Novel Framework for Causal Inference in Bayesian Networks
  40. Thompson Sampling-like Algorithms for Stochastic Rising Bandits
  41. Personalized Author Obfuscation with Large Language Models
  42. NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Results
  43. Discovering Symbolic Differential Equations with Symmetry Invariants
  44. SepPrune: Structured Pruning for Efficient Deep Speech Separation
  45. Integrative Analysis and Imputation of Multiple Data Streams via Deep Gaussian Processes
  46. Do different prompting methods yield a common task representation in language models?
  47. Denoising Mutual Knowledge Distillation in Bi-Directional Multiple Instance Learning
  48. Historical and psycholinguistic perspectives on morphological productivity: A sketch of an integrative approach
  49. MT-CYP-Net: Multi-Task Network for Pixel-Level Crop Yield Prediction Under Very Few Samples
  50. Beluga Whale Detection from Satellite Imagery with Point Labels
  51. Bayesian Deep Learning Approaches for Uncertainty-Aware Retinal OCT Image Segmentation for Multiple Sclerosis
  52. Tiny QA Benchmark++: Ultra-Lightweight, Synthetic Multilingual Dataset Generation & Smoke-Tests for Continuous LLM Evaluation
  53. CorBenchX: Large-Scale Chest X-Ray Error Dataset and Vision-Language Model Benchmark for Report Error Correction
  54. GenderBench: Evaluation Suite for Gender Biases in LLMs
  55. Enhanced Multimodal Hate Video Detection via Channel-wise and Modality-wise Fusion
  56. Beyond Scalar Rewards: An Axiomatic Framework for Lexicographic MDPs
  57. Unsupervised Port Berth Identification from Automatic Identification System Data
  58. FIGhost: Fluorescent Ink-based Stealthy and Flexible Backdoor Attacks on Physical Traffic Sign Recognition
  59. FlashBias: Fast Computation of Attention with Bias
  60. MoL for LLMs: Dual-Loss Optimization to Enhance Domain Expertise While Preserving General Capabilities
  61. Improving regional weather forecasts with neural interpolation
  62. AI-Driven Automation Can Become the Foundation of Next-Era Science of Science Research
  63. Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets
  64. Adaptive Resolving Methods for Markov Decision Processes with Function Approximations
  65. Towards Comprehensive Argument Analysis in Education: Dataset, Tasks, and Method
  66. Relation-Aware Graph Foundation Model
  67. Spotlight Your Instructions: Instruction-following with Dynamic Attention Steering
  68. Cross-Model Transfer of Task Vectors via Few-Shot Orthogonal Alignment
  69. FL-PLAS: Federated Learning with Partial Layer Aggregation for Backdoor Defense Against High-Ratio Malicious Clients
  70. Empowering Sustainable Finance with Artificial Intelligence: A Framework for Responsible Implementation
  71. Incentivize Contribution and Learn Parameters Too: Federated Learning with Strategic Data Owners
  72. LatentStealth: Unnoticeable and Efficient Adversarial Attacks on Expressive Human Pose and Shape Estimation
  73. CHRIS: Clothed Human Reconstruction with Side View Consistency
  74. Approximation theory for 1-Lipschitz ResNets
  75. MRGRP: Empowering Courier Route Prediction in Food Delivery Service with Multi-Relational Graph
  76. Parameter Efficient Continual Learning with Dynamic Low-Rank Adaptation
  77. Multimodal Cancer Survival Analysis via Hypergraph Learning with Cross-Modality Rebalance
  78. Variance-Optimal Arm Selection: Misallocation Minimization and Best Arm Identification
  79. Multi-Attribute Graph Estimation with Sparse-Group Non-Convex Penalties
  80. Online Iterative Self-Alignment for Radiology Report Generation
  81. FedHQ: Hybrid Runtime Quantization for Federated Learning
  82. AoP-SAM: Automation of Prompts for Efficient Segmentation
  83. Introduction to Analytical Software Engineering Design Paradigm
  84. Advanced Integration of Discrete Line Segments in Digitized P&ID for Continuous Instrument Connectivity
  85. Accelerating Neural Network Training Along Sharp and Flat Directions
  86. An Annotated Corpus of Arabic Tweets for Hate Speech Analysis
  87. CCNU at SemEval-2025 Task 3: Leveraging Internal and External Knowledge of Large Language Models for Multilingual Hallucination Annotation
  88. CrafText Benchmark: Advancing Instruction Following in Complex Multimodal Open-Ended World
  89. EmoHopeSpeech: An Annotated Dataset of Emotions and Hope Speech in English and Arabic
  90. Counterspeech the ultimate shield! Multi-Conditioned Counterspeech Generation through Attributed Prefix Learning
  91. Top-Down Compression: Revisit Efficient Vision Token Projection for Visual Instruction Tuning
  92. FOCAL: Fine-Grained Optimal-Transport-Driven Contrastive Alignment of Language and ECGs with Waveform Enhancement
  93. iSegMan: Interactive Segment-and-Manipulate 3D Gaussians
  94. Conversational Recommendation System using NLP and Sentiment Analysis
  95. The Logical Expressiveness of Temporal GNNs via Two-Dimensional Product Logics
  96. PyScrew: A Comprehensive Dataset Collection from Industrial Screw Driving Experiments
  97. Enhancing Complex Instruction Following for Large Language Models with Mixture-of-Contexts Fine-tuning
  98. DC-Seg: Disentangled Contrastive Learning for Brain Tumor Segmentation with Missing Modalities
  99. Transformers as Unsupervised Learning Algorithms: A study on Gaussian Mixtures
  100. Joint Manifold Learning and Optimal Transport for Dynamic Imaging
  101. Mod`eles de Substitution pour les Mod`eles `a base d'Agents : Enjeux, M'ethodes et Applications
  102. Improving the discovery of near-Earth objects with machine-learning methods
  103. Bridging the Inter-Domain Gap through Low-Level Features for Cross-Modal Medical Image Segmentation
  104. GTR: Gaussian Splatting Tracking and Reconstruction of Unknown Objects Based on Appearance and Geometric Complexity
  105. K*-Means: A Parameter-free Clustering Algorithm
  106. Dynamic Perturbed Adaptive Method for Infinite Task-Conflicting Time Series
  107. Recursive Question Understanding for Complex Question Answering over Heterogeneous Personal Data
  108. From Recall to Reasoning: Automated Question Generation for Deeper Math Learning through Large Language Models
  109. Adversarial Robustness for Unified Multi-Modal Encoders via Efficient Calibration
  110. Fast RoPE Attention: Combining the Polynomial Method and Fast Fourier Transform
  111. Revisiting SSL for sound event detection: complementary fusion and adaptive post-processing
  112. AutoMedEval: Harnessing Language Models for Automatic Medical Capability Evaluation
  113. Facial Recognition Leveraging Generative Adversarial Networks
  114. MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging
  115. GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder
  116. Revisiting Residual Connections: Orthogonal Updates for Stable and Efficient Deep Networks
  117. Experimental Study on Automatically Assembling Custom Catering Packages With a 3-DOF Delta Robot Using Deep Learning Methods
  118. AdaptMol: Adaptive Fusion from Sequence String to Topological Structure for Few-shot Drug Discovery
  119. EAMET: Robust Massive Model Editing via Embedding Alignment Optimization
  120. MonoMobility: Zero-Shot 3D Mobility Analysis from Monocular Videos
  121. Position Paper: Bounded Alignment: What (Not) To Expect From AGI Agents
  122. GLOVER++: Unleashing the Potential of Affordance Learning from Human Behaviors for Robotic Manipulation
  123. When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Research
  124. Bridging the Reality Gap in Digital Twins with Context-Aware, Physics-Guided Deep Learning
  125. Learning on a Razor's Edge: Identifiability and Singularity of Polynomial Neural Networks
  126. ElderFallGuard: Real-Time IoT and Computer Vision-Based Fall Detection System for Elderly Safety
  127. S-Crescendo: A Nested Transformer Weaving Framework for Scalable Nonlinear System in S-Domain Representation
  128. On the O(frac√dK1/4) Convergence Rate of AdamW Measured by ℓ1 Norm
  129. Patient-Specific Autoregressive Models for Organ Motion Prediction in Radiotherapy
  130. Class Distillation with Mahalanobis Contrast: An Efficient Training Paradigm for Pragmatic Language Understanding Tasks
  131. Variational Regularized Unbalanced Optimal Transport: Single Network, Least Action
  132. Robust Drone-View Geo-Localization via Content-Viewpoint Disentanglement
  133. Chain-of-Model Learning for Language Model
  134. AnalyticKWS: Towards Exemplar-Free Analytic Class Incremental Learning for Small-footprint Keyword Spotting
  135. Continuous Subspace Optimization for Continual Learning
  136. ChatHTN: Interleaving Approximate (LLM) and Symbolic HTN Planning
  137. VenusX: Unlocking Fine-Grained Functional Understanding of Proteins
  138. Efficiently Building a Domain-Specific Large Language Model from Scratch: A Case Study of a Classical Chinese Large Language Model
  139. VITA: Versatile Time Representation Learning for Temporal Hyper-Relational Knowledge Graphs
  140. Diffmv: A Unified Diffusion Framework for Healthcare Predictions with Random Missing Views and View Laziness
  141. CL-BioGAN: Biologically-Inspired Cross-Domain Continual Learning for Hyperspectral Anomaly Detection
  142. CL-CaGAN: Capsule differential adversarial continuous learning for cross-domain hyperspectral anomaly detection
  143. Solver-Informed RL: Grounding Large Language Models for Authentic Optimization Modeling
  144. Communication-Efficient Hybrid Language Model via Uncertainty-Aware Opportunistic and Compressed Transmission
  145. Multi-Order Wavelet Derivative Transform for Deep Time Series Forecasting
  146. A Review and Analysis of a Parallel Approach for Decision Tree Learning from Large Data Streams
  147. Generative and Contrastive Graph Representation Learning
  148. HARDMath2: A Benchmark for Applied Mathematics Built by Students as Part of a Graduate Class
  149. LAMP: Extracting Local Decision Surfaces From Large Language Models
  150. Residual Feature Integration is Sufficient to Prevent Negative Transfer
  151. Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors
  152. Technical Report for ICRA 2025 GOOSE 2D Semantic Segmentation Challenge: Boosting Off-Road Segmentation via Photometric Distortion and Exponential Moving Average
  153. Reformulating Neural Operators in d+1 Dimensions for Embedding Evolution
  154. Towards Universal Semantics With Large Language Models