LLM Safety From Within: Detecting Harmful Content with Internal Representations Paper • 2604.18519 • Published 16 days ago • 23
DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstruction Paper • 2604.21518 • Published 13 days ago • 28
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond Paper • 2604.22748 • Published 12 days ago • 222
RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time Paper • 2604.11626 • Published 23 days ago • 101
InCoder-32B-Thinking: Industrial Code World Model for Thinking Paper • 2604.03144 • Published Apr 3 • 233
DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Histories Paper • 2602.10809 • Published Feb 11 • 59
QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining Paper • 2602.07085 • Published Feb 6 • 190
Closing the Loop: Universal Repository Representation with RPG-Encoder Paper • 2602.02084 • Published Feb 2 • 85
Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives Paper • 2601.20833 • Published Jan 28 • 183
EvasionBench: Detecting Evasive Answers in Financial Q&A via Multi-Model Consensus and LLM-as-Judge Paper • 2601.09142 • Published Jan 14 • 10
Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows Paper • 2512.13168 • Published Dec 15, 2025 • 53
StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs Paper • 2509.22220 • Published Sep 26, 2025 • 66
SWE-QA: Can Language Models Answer Repository-level Code Questions? Paper • 2509.14635 • Published Sep 18, 2025 • 35
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 • 63
Table-R1: Inference-Time Scaling for Table Reasoning Paper • 2505.23621 • Published May 29, 2025 • 93
Sherlock: Self-Correcting Reasoning in Vision-Language Models Paper • 2505.22651 • Published May 28, 2025 • 47
OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization Data Paper • 2505.18445 • Published May 24, 2025 • 63
PixelHacker: Image Inpainting with Structural and Semantic Consistency Paper • 2504.20438 • Published Apr 29, 2025 • 44