Papers

New on arXiv

Sat 12 Apr 2025

144 papers

Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference TimeLLM reasoning → Test-time compute and efficient thinking
A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and FutureLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
HeteRAG: A Heterogeneous Retrieval-augmented Generation Framework with Decoupled Knowledge RepresentationsRetrieval-augmented generation → RAG pipeline design and evaluation
MoE-Lens: Towards the Hardware Limit of High-Throughput MoE LLM Serving Under Resource ConstraintsMixture-of-experts → Efficient MoE training and inference systems +1
Context-Aware Adaptive Sampling for Intelligent Data Acquisition Systems Using DQNDeep reinforcement learning methods → RL for energy, networks and operations
Towards Optimal Differentially Private Regret Bounds in Linear MDPsDeep reinforcement learning methods → RL for energy, networks and operations
Efficient Implementation of Reinforcement Learning over Homomorphic EncryptionDeep reinforcement learning methods → RL for energy, networks and operations
MedIL: Implicit Latent Spaces for Generating Heterogeneous Medical Images at Arbitrary ResolutionsDiffusion models → Medical imaging and segmentation
Continuum-Interaction-Driven Intelligence: Human-Aligned Neural Architecture via Crystallized Reasoning and Fluid GenerationLLM reasoning → Reasoning benchmarks and evaluation
DynaServe: Unified and Elastic Execution for Dynamic Disaggregated LLM ServingEfficient LLM inference and serving → Serving systems and request scheduling
Mixture of Group Experts for Learning Invariant RepresentationsMixture-of-experts → Vision mixture-of-experts
Head-Aware KV Cache Compression for Efficient Visual Autoregressive ModelingEfficient LLM inference and serving → Fast autoregressive visual generation
PathVLM-R1: A Reinforcement Learning-Driven Reasoning Model for Pathology Visual-Language TasksLLM reasoning → Clinical and biomedical applications +1
Development of a PPO-Reinforcement Learned Walking Tripedal Soft-Legged Robot using SOFADeep reinforcement learning methods → RL for robot locomotion and manipulation
Generation of Musical Timbres using a Text-Guided Diffusion ModelDiffusion models → Audio, speech and music
Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End SystemRetrieval-augmented generation → RAG robustness and adaptive retrieval
From Visual Explanations to Counterfactual Explanations with Latent DiffusionDiffusion models → Diffusion foundations and sampling
Repetitive Contrastive Learning Enhances Mamba's Selectivity in Time Series PredictionState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
VisuoThink: Empowering LVLM Reasoning with Multimodal Tree SearchLLM reasoning → Multimodal reasoning +1
A Short Survey on Small Reasoning Models: Training, Inference, Applications and Research DirectionsLLM reasoning → Reasoning benchmarks and evaluation
Using Vision Language Models for Safety Hazard Identification in ConstructionMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
UniFlowRestore: A General Video Restoration Framework via Flow Matching and Prompt GuidanceDiffusion models → Inverse problems and image restoration
Towards Stepwise Domain Knowledge-Driven Reasoning Optimization and Reflection ImprovementLLM reasoning → Prompting and chain-of-thought reasoning
Sculpting Memory: Multi-Concept Forgetting in Diffusion Models via Dynamic Mask and Concept-Aware OptimizationDiffusion models → Robustness, privacy and adversarial aspects +1
A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic SystemsLLM reasoning → Reasoning for agents, planning and code +1
InterQ: A DQN Framework for Optimal Intermittent ControlDeep reinforcement learning methods → Deep RL algorithms and representations
A Champion-level Vision-based Reinforcement Learning Agent for Competitive Racing in Gran Turismo 7Deep reinforcement learning methods → RL for autonomous driving and traffic
Laser Scan Path Design for Controlled Microstructure in Additive Manufacturing with Integrated Reduced-Order Phase-Field Modeling and Deep Reinforcement Learning
HER2 Expression Prediction with Flexible Multi-Modal Inputs via Dynamic Bidirectional Reconstruction
BrainPrompt: Multi-Level Brain Prompt Enhancement for Neurological Condition Identification
Universal Representations for Classification-enhanced Lossy Compression
Word Embeddings Track Social Group Changes Across 70 Years in China
Reconstructing Sepsis Trajectories from Clinical Case Reports using LLMs: the Textual Time Series Corpus for Sepsis
Flux Already Knows -- Activating Subject-Driven Image Generation without Training
SDIGLM: Leveraging Large Language Models and Multi-Modal Chain of Thought for Structural Damage Identification
CI-RKM: A Class-Informed Approach to Robust Restricted Kernel Machines
Local Temporal Feature Enhanced Transformer with ROI-rank Based Masking for Diagnosis of ADHD
Visual moral inference and communication
Explainable Artificial Intelligence Techniques for Interpretation of Food Models: a Review
PathSeqSAM: Sequential Modeling for Pathology Image Segmentation with SAM2
BioChemInsight: An Online Platform for Automated Extraction of Chemical Structures and Activity Data from Patents
Gradient as Conditions: Rethinking HOG for All-in-one Image Restoration
QUDsim: Quantifying Discourse Similarities in LLM-Generated Text
Machine Learning-Based Cyberattack Detection and Identification for Automatic Generation Control Systems Considering Nonlinearities
PapMOT: Exploring Adversarial Patch Attack against Multiple Object Tracking
REMEMBER: Retrieval-based Explainable Multimodal Evidence-guided Modeling for Brain Evaluation and Reasoning in Zero- and Few-shot Neurodegenerative Diagnosis
Explorer: Robust Collection of Interactable GUI Elements
Neural Posterior Estimation on Exponential Random Graph Models: Evaluating Bias and Implementation Challenges
Graph-Based Prediction Models for Data Debiasing
Inference for Deep Neural Network Estimators in Generalized Nonparametric Models
"It's not a representation of me": Examining Accent Bias and Digital Exclusion in Synthetic AI Voice Services
Confirmation Bias in Generative AI Chatbots: Mechanisms, Risks, Mitigation Strategies, and Future Research Directions
Minority Reports: Balancing Cost and Quality in Ground Truth Data Annotation
Building Machine Learning Limited Area Models: Kilometer-Scale Weather Forecasting in Realistic Settings
Regretful Decisions under Label Noise
Text To 3D Object Generation For Scalable Room Assembly
Infused Suppression Of Magnification Artefacts For Micro-AU Detection
Conformal Calibration: Ensuring the Reliability of Black-Box AI in Wireless Systems
Improving the Accuracy and Efficiency of Legal Document Tagging with Large Language Models and Instruction Prompts
Lumos: Efficient Performance Modeling and Estimation for Large-scale LLM Training
Enhancing Contrastive Demonstration Selection with Semantic Diversity for Robust In-Context Machine Translation
Application of Contrastive Learning on ECG Data: Evaluating Performance in Japanese and Classification with Around 100 Labels
Beyond Glucose-Only Assessment: Advancing Nocturnal Hypoglycemia Prediction in Children with Type 1 Diabetes
A Lightweight Moment Retrieval System with Global Re-Ranking and Robust Adaptive Bidirectional Temporal Search
Cycle Training with Semi-Supervised Domain Adaptation: Bridging Accuracy and Efficiency for Real-Time Mobile Scene Detection
Towards Explainable Partial-AIGC Image Quality Assessment
Sparse Hybrid Linear-Morphological Networks
Semantic Commit: Helping Users Update Intent Specifications for AI Memory at Scale
VideoAds for Fast-Paced Video Understanding
No-Regret Generative Modeling via Parabolic Monge-Amp`ere PDE
SynthTRIPs: A Knowledge-Grounded Framework for Benchmark Query Generation for Personalized Tourism Recommenders
Linguistic Comparison of AI- and Human-Written Responses to Online Mental Health Queries
NetTAG: A Multimodal RTL-and-Layout-Aligned Netlist Foundation Model via Text-Attributed Graph
MiMIC: Multi-Modal Indian Earnings Calls Dataset to Predict Stock Prices
FVQ: A Large-Scale Dataset and an LMM-based Method for Face Video Quality Assessment
Adiabatic Encoding of Pre-trained MPS Classifiers into Quantum Circuits
NoTeS-Bank: Benchmarking Neural Transcription and Search for Scientific Notes Understanding
Type-Constrained Code Generation with Language Models
Learning Occlusion-Robust Vision Transformers for Real-Time UAV Tracking
AMNet: An Acoustic Model Network for Enhanced Mandarin Speech Synthesis
DL-QAT: Weight-Decomposed Low-Rank Quantization-Aware Training for Large Language Models
CMCRD: Cross-Modal Contrastive Representation Distillation for Emotion Recognition
Multi-scale Activation, Refinement, and Aggregation: Exploring Diverse Cues for Fine-Grained Bird Recognition
Spiking Neural Network for Intra-cortical Brain Signal Decoding
Accurate Diagnosis of Respiratory Viruses Using an Explainable Machine Learning with Mid-Infrared Biomolecular Fingerprinting of Nasopharyngeal Secretions
FairACE: Achieving Degree Fairness in Graph Neural Networks via Contrastive and Adversarial Group-Balanced Training
EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation
Rethinking Remaining Useful Life Prediction with Scarce Time Series Data: Regression under Indirect Supervision
Query-based Knowledge Transfer for Heterogeneous Learning Environments
AerOSeg: Harnessing SAM for Open-Vocabulary Segmentation in Remote Sensing Images
Graph Learning-Driven Multi-Vessel Association: Fusing Multimodal Data for Maritime Intelligence
RT-DATR: Real-time Unsupervised Domain Adaptive Detection Transformer with Adversarial Feature Alignment
ReferGPT: Towards Zero-Shot Referring Multi-Object Tracking
Towards More Efficient, Robust, Instance-adaptive, and Generalizable Sequential Decision making
Feature-Aware Malicious Output Detection and Mitigation
Parameterized Synthetic Text Generation with SimpleStories
seg2med: a bridge from artificial anatomy to multimodal medical images
A Confounding Factors-Inhibition Adversarial Learning Framework for Multi-site fMRI Mental Disorder Identification
Langformers: Unified NLP Pipelines for Language Models
Can postgraduate translation students identify machine-generated text?

All 144