| DB-KSVD: Scalable Alternating Optimization for Disentangling High-Dimensional Embedding Spaces | May 24, 2025 | Dictionary Learning | CodeCode Available | 1 |
| MSLAU-Net: A Hybird CNN-Transformer Network for Medical Image Segmentation | May 24, 2025 | Image SegmentationMedical Image Segmentation | CodeCode Available | 1 |
| Cross-Lingual Pitfalls: Automatic Probing Cross-Lingual Weakness of Multilingual Large Language Models | May 24, 2025 | | CodeCode Available | 1 |
| OmniGenBench: A Benchmark for Omnipotent Multimodal Generation across 50+ Tasks | May 24, 2025 | Image GenerationInstruction Following | CodeCode Available | 1 |
| MonarchAttention: Zero-Shot Conversion to Fast, Hardware-Aware Structured Attention | May 24, 2025 | 16k4k | CodeCode Available | 1 |
| MLRan: A Behavioural Dataset for Ransomware Analysis and Detection | May 24, 2025 | feature selection | CodeCode Available | 1 |
| Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework | May 24, 2025 | Adversarial AttackSpeech Tokenization | CodeCode Available | 1 |
| Flex-Judge: Think Once, Judge Anywhere | May 24, 2025 | | CodeCode Available | 1 |
| VORTA: Efficient Video Diffusion via Routing Sparse Attention | May 24, 2025 | Video Generation | CodeCode Available | 1 |
| Smoothie: Smoothing Diffusion on Token Embeddings for Text Generation | May 24, 2025 | Semantic SimilaritySemantic Textual Similarity | CodeCode Available | 1 |
| Removal of Hallucination on Hallucination: Debate-Augmented RAG | May 24, 2025 | HallucinationRAG | CodeCode Available | 1 |
| Signal, Image, or Symbolic: Exploring the Best Input Representation for Electrocardiogram-Language Models Through a Unified Framework | May 24, 2025 | | CodeCode Available | 1 |
| GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis | May 24, 2025 | RAGRetrieval | CodeCode Available | 1 |
| Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting | May 24, 2025 | Time SeriesTime Series Forecasting | CodeCode Available | 1 |
| ThanoRA: Task Heterogeneity-Aware Multi-Task Low-Rank Adaptation | May 24, 2025 | Mixture-of-Experts | CodeCode Available | 1 |
| Generative Distribution Embeddings | May 23, 2025 | | CodeCode Available | 1 |
| VEAttack: Downstream-agnostic Vision Encoder Attack against Large Vision Language Models | May 23, 2025 | Question AnsweringVisual Question Answering | CodeCode Available | 1 |
| PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation | May 23, 2025 | Pose Estimation | CodeCode Available | 1 |
| IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis | May 23, 2025 | Instruction Following | CodeCode Available | 1 |
| UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic information | May 23, 2025 | Large Language ModelQuantization | CodeCode Available | 1 |
| BEDI: A Comprehensive Benchmark for Evaluating Embodied Agents on UAVs | May 23, 2025 | Model OptimizationTask Planning | CodeCode Available | 1 |
| Co-Reinforcement Learning for Unified Multimodal Understanding and Generation | May 23, 2025 | Image Generationreinforcement-learning | CodeCode Available | 1 |
| Value-Guided Search for Efficient Chain-of-Thought Reasoning | May 23, 2025 | Math | CodeCode Available | 1 |
| RaDeR: Reasoning-aware Dense Retrieval Models | May 23, 2025 | MathMathematical Problem-Solving | CodeCode Available | 1 |
| Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms | May 23, 2025 | Language ModelingLanguage Modelling | CodeCode Available | 1 |
| Frankentext: Stitching random text fragments into long-form narratives | May 23, 2025 | Form | CodeCode Available | 1 |
| MetaGen Blended RAG: Higher Accuracy for Domain-Specific Q&A Without Fine-Tuning | May 23, 2025 | Few-Shot LearningQuestion Answering | CodeCode Available | 1 |
| HRSim: An agent-based simulation platform for high-capacity ride-sharing services | May 23, 2025 | | CodeCode Available | 1 |
| RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning | May 23, 2025 | Image GenerationLanguage Modeling | CodeCode Available | 1 |
| Taming Diffusion for Dataset Distillation with High Representativeness | May 23, 2025 | Dataset DistillationImage Generation | CodeCode Available | 1 |
| The Cell Must Go On: Agar.io for Continual Reinforcement Learning | May 23, 2025 | Continual LearningDeep Reinforcement Learning | CodeCode Available | 1 |
| CENet: Context Enhancement Network for Medical Image Segmentation | May 23, 2025 | DecoderImage Segmentation | CodeCode Available | 1 |
| Benchmarking Recommendation, Classification, and Tracing Based on Hugging Face Knowledge Graph | May 23, 2025 | BenchmarkingManagement | CodeCode Available | 1 |
| Towards Revealing the Effectiveness of Small-Scale Fine-tuning in R1-style Reinforcement Learning | May 23, 2025 | MathReinforcement Learning (RL) | CodeCode Available | 1 |
| Revisiting Feature Interactions from the Perspective of Quadratic Neural Networks for Click-through Rate Prediction | May 23, 2025 | Click-Through Rate PredictionRecommendation Systems | CodeCode Available | 1 |
| Object-level Cross-view Geo-localization with Location Enhancement and Multi-Head Cross Attention | May 23, 2025 | Few-Shot Learninggeo-localization | CodeCode Available | 1 |
| T2VUnlearning: A Concept Erasing Method for Text-to-Video Diffusion Models | May 23, 2025 | | CodeCode Available | 1 |
| Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Models | May 23, 2025 | MambaTime Series Classification | CodeCode Available | 1 |
| Reinforcement Learning for Ballbot Navigation in Uneven Terrain | May 23, 2025 | MuJoCoreinforcement-learning | CodeCode Available | 1 |
| REN: Fast and Efficient Region Encodings from Patch-Based Image Encoders | May 23, 2025 | Semantic Segmentation | CodeCode Available | 1 |
| Universal Biological Sequence Reranking for Improved De Novo Peptide Sequencing | May 23, 2025 | de novo peptide sequencingReranking | CodeCode Available | 1 |
| Center-aware Residual Anomaly Synthesis for Multi-class Industrial Anomaly Detection | May 23, 2025 | Anomaly DetectionMulti-class Anomaly Detection | CodeCode Available | 1 |
| Knot So Simple: A Minimalistic Environment for Spatial Reasoning | May 23, 2025 | Model Predictive ControlSpatial Reasoning | CodeCode Available | 1 |
| Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities | May 23, 2025 | Automatic Speech RecognitionAutomatic Speech Recognition (ASR) | CodeCode Available | 1 |
| Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human States | May 23, 2025 | Theory of Mind Modeling | CodeCode Available | 1 |
| Semantic Correspondence: Unified Benchmarking and a Strong Baseline | May 23, 2025 | BenchmarkingSemantic correspondence | CodeCode Available | 1 |
| ManuSearch: Democratizing Deep Search in Large Language Models with a Transparent and Open Multi-Agent Framework | May 23, 2025 | | CodeCode Available | 1 |
| The Origins of Representation Manifolds in Large Language Models | May 23, 2025 | | CodeCode Available | 1 |
| Twin-2K-500: A dataset for building digital twins of over 2,000 people based on their answers to over 500 questions | May 23, 2025 | 2kBenchmarking | CodeCode Available | 1 |
| Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens | May 23, 2025 | Large Language Model | CodeCode Available | 1 |
