REBASE: Reference-Background Subspace Elimination for Training-Free In-Context Segmentation Paper • 2607.09082 • Published 17 days ago • 26
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget Paper • 2607.14952 • Published 11 days ago • 200
Navigating the Mirage: A Dual-Path Agentic Framework for Robust Misleading Chart Question Answering Paper • 2603.28583 • Published 13 days ago • 17
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published May 28 • 252
EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation Paper • 2605.23271 • Published May 22 • 81
IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools Paper • 2605.20682 • Published May 20 • 85
EndPrompt: Efficient Long-Context Extension via Terminal Anchoring Paper • 2605.14589 • Published May 14 • 18
Multi-Objective and Mixed-Reward Reinforcement Learning via Reward-Decorrelated Policy Optimization Paper • 2605.13641 • Published May 13 • 51
Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation Paper • 2605.03849 • Published May 5 • 129
The Geometric Alignment Tax: Tokenization vs. Continuous Geometry in Scientific Foundation Models Paper • 2604.04155 • Published Apr 5 • 14
Colon-Bench: An Agentic Workflow for Scalable Dense Lesion Annotation in Full-Procedure Colonoscopy Videos Paper • 2603.25645 • Published Mar 26 • 4
InCoder-32B: Code Foundation Model for Industrial Scenarios Paper • 2603.16790 • Published Mar 17 • 312
HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions Paper • 2603.15612 • Published Mar 16 • 153
DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval Paper • 2603.04743 • Published Mar 5 • 54