Submitted by Swtheking 50 AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning · 9 authors 2
Submitted by gmlwns5176 46 Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction · 3 authors 2
Submitted by tianbaoxiexxx 40 Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis · 15 authors 2
Submitted by zlzheng 25 Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space · 11 authors 4
Submitted by Vasily 24 Through the Looking Glass: Common Sense Consistency Evaluation of Weird Images · 6 authors 2
Submitted by Cierra0506 22 MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervision · 7 authors 2
Submitted by ohseungjun 22 Hybrid 3D-4D Gaussian Splatting for Fast Dynamic Scene Representation · 4 authors 1
Submitted by Zkkkai 22 CPGD: Toward Stable Rule-based Reinforcement Learning for Language Models · 7 authors 2
Submitted by Sangsang 21 FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA · 8 authors 3
Submitted by lytang 16 ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models · 15 authors 3
Submitted by Dreamer312 15 SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization · 4 authors 3
Submitted by zszhong 14 VisionReasoner: Unified Visual Perception and Reasoning via Reinforcement Learning · 7 authors 2
Submitted by merlerm 13 ViPlan: A Benchmark for Visual Planning with Symbolic Predicates and Vision-Language Models · 8 authors 1
Submitted by amphora 9 When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Research · 11 authors 2
Submitted by Paulmzr 7 Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space · 6 authors 2
Submitted by yanboding 7 MTVCrafter: 4D Motion Tokenization for Open-World Human Image Animation · 4 authors 2
Submitted by vincentkoc 6 Tiny QA Benchmark++: Ultra-Lightweight, Synthetic Multilingual Dataset Generation & Smoke-Tests for Continuous LLM Evaluation · 1 authors 3
Submitted by xuyige 5 SoftCoT++: Test-Time Scaling with Soft Chain-of-Thought Reasoning · 4 authors 2
Submitted by Harold328 4 FinePhys: Fine-grained Human Action Generation by Explicitly Incorporating Physical Laws for Effective Skeletal Guidance · 6 authors 1
Submitted by Krystalan 3 ExTrans: Multilingual Deep Reasoning Translation via Exemplar-Enhanced Reinforcement Learning · 3 authors 2
Submitted by mgvz 3 HISTAI: An Open-Source, Large-Scale Whole Slide Image Dataset for Computational Pathology · 3 authors 2
Submitted by minwoosun 3 MedCaseReasoning: Evaluating and learning diagnostic reasoning from clinical case reports · 10 authors 2
Submitted by Ksgk-fy 2 From Grunts to Grammar: Emergent Language from Cooperative Foraging · 7 authors 2
Submitted by JitaiHao 2 A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone · 6 authors 2
Submitted by lekssays 2 TechniqueRAG: Retrieval Augmented Generation for Adversarial Technique Annotation in Cyber Threat Intelligence Text · 4 authors 2
Submitted by zhilinw 2 HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages · 9 authors 2
Submitted by PChemGuy 1 LLM Context Conditioning and PWP Prompting for Multimodal Validation of Chemical Formulas · 1 authors 2
Submitted by PChemGuy 1 AI-Driven Scholarly Peer Review via Persistent Workflow Prompting, Meta-Prompting, and Meta-Reasoning · 1 authors 2
Submitted by MahtaFetrat - Fast, Not Fancy: Rethinking G2P with Rich Data and Rule-Based Models · 3 authors 2
Submitted by dnoever - Can AI Freelancers Compete? Benchmarking Earnings, Reliability, and Task Success at Scale · 2 authors 2