FlowAnchor: Stabilizing the Editing Signal for Inversion-Free Video Editing Paper • 2604.22586 • Published Apr 24 • 16
LLM Safety From Within: Detecting Harmful Content with Internal Representations Paper • 2604.18519 • Published Apr 20 • 26
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond Paper • 2604.22748 • Published Apr 24 • 227
InCoder-32B-Thinking: Industrial Code World Model for Thinking Paper • 2604.03144 • Published Apr 3 • 237
HyTRec: A Hybrid Temporal-Aware Attention Architecture for Long Behavior Sequential Recommendation Paper • 2602.18283 • Published Feb 20 • 57
InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery Paper • 2602.08990 • Published Feb 9 • 78
QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining Paper • 2602.07085 • Published Feb 6 • 191
Length-Unbiased Sequence Policy Optimization: Revealing and Controlling Response Length Variation in RLVR Paper • 2602.05261 • Published Feb 5 • 53
Closing the Loop: Universal Repository Representation with RPG-Encoder Paper • 2602.02084 • Published Feb 2 • 85
Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows Paper • 2512.13168 • Published Dec 15, 2025 • 54
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length Paper • 2512.04677 • Published Dec 4, 2025 • 178
LongCodeZip: Compress Long Context for Code Language Models Paper • 2510.00446 • Published Oct 1, 2025 • 108
StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs Paper • 2509.22220 • Published Sep 26, 2025 • 66
RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation Paper • 2509.16198 • Published Sep 19, 2025 • 129
MachineLearningLM: Continued Pretraining Language Models on Millions of Synthetic Tabular Prediction Tasks Scales In-Context ML Paper • 2509.06806 • Published Sep 8, 2025 • 64
PaSa: An LLM Agent for Comprehensive Academic Paper Search Paper • 2501.10120 • Published Jan 17, 2025 • 55
Multiple Choice Questions: Reasoning Makes Large Language Models (LLMs) More Self-Confident Even When They Are Wrong Paper • 2501.09775 • Published Jan 16, 2025 • 32
VideoWorld: Exploring Knowledge Learning from Unlabeled Videos Paper • 2501.09781 • Published Jan 16, 2025 • 27