Submitted by xyma 102 ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability · 7 authors 93 4
Submitted by X-iZhang 68 A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems · 15 authors 61 2
Submitted by xiaochonglinghu 52 Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation · 10 authors 104 3
Submitted by MrLight 35 BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent · 20 authors 42 2
Submitted by Suu 32 Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization · 8 authors 27 3
Submitted by razzant 31 SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Speaks in Tokens · 5 authors 10 2
Submitted by chengq9 26 UserBench: An Interactive Gym Environment for User-Centric Agents · 12 authors 26 4
Submitted by CheeryLJH 22 Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning · 15 authors 3
Submitted by Monta3Pt 20 Spectrum Projection Score: Aligning Retrieved Summaries with Reader Models in Retrieval-Augmented Generation · 6 authors 2
Submitted by hywu 15 Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts · 13 authors 7 2
Submitted by qianlanwyd 13 Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future · 12 authors 2
Submitted by drkylj 12 Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning · 8 authors 2
Submitted by FrankLuox 10 Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation · 6 authors 2
Submitted by Dunge0nMaster 9 Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control · 9 authors 2
Submitted by XiaodongChen 8 MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMs · 5 authors 3 2
Submitted by stefan-it 7 GLiClass: Generalist Lightweight Model for Sequence Classification Tasks · 6 authors 154 2
Submitted by puar-playground 7 VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding · 9 authors 4 2
Submitted by stellaathena 5 Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs · 10 authors 2
Submitted by j-min 5 Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents · 5 authors 20 2
Submitted by clem 3 Anatomy of a Machine Learning Ecosystem: 2 Million Models on Hugging Face · 3 authors 4
Submitted by HarryHe 3 Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System · 6 authors 2
Submitted by marsianin500 3 Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences · 9 authors 2
Submitted by oneonlee 2 When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs · 8 authors 2
Submitted by justinphan3110 1 TextQuests: How Good are LLMs at Text-Based Video Games? · 4 authors 8 2