LangFlow: Continuous Diffusion Rivals Discrete in Language Modeling Paper • 2604.11748 • Published 10 days ago • 14
Narrative-Driven Paper-to-Slide Generation via ArcDeck Paper • 2604.11969 • Published 12 days ago • 7
MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models Paper • 2603.28590 • Published 26 days ago • 22
MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models Paper • 2603.28590 • Published 26 days ago • 22
HandX: Scaling Bimanual Motion and Interaction Generation Paper • 2603.28766 • Published 26 days ago • 12
Sparking Scientific Creativity via LLM-Driven Interdisciplinary Inspiration Paper • 2603.12226 • Published Mar 12 • 4
Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data Paper • 2602.21320 • Published Feb 24 • 12
Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs Paper • 2602.07276 • Published Feb 7 • 11
CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs Paper • 2602.07080 • Published Feb 6 • 6
Embodied Referring Expression Comprehension in Human-Robot Interaction Paper • 2512.06558 • Published Dec 6, 2025 • 3
Drift No More? Context Equilibria in Multi-Turn LLM Interactions Paper • 2510.07777 • Published Oct 9, 2025
MIRAGE: A Benchmark for Multimodal Information-Seeking and Reasoning in Agricultural Expert-Guided Conversations Paper • 2506.20100 • Published Jun 25, 2025 • 1
Plan Verification for LLM-Based Embodied Task Completion Agents Paper • 2509.02761 • Published Sep 2, 2025
oMeBench: Towards Robust Benchmarking of LLMs in Organic Mechanism Elucidation and Reasoning Paper • 2510.07731 • Published Oct 9, 2025 • 6
HalluSegBench: Counterfactual Visual Reasoning for Segmentation Hallucination Evaluation Paper • 2506.21546 • Published Jun 26, 2025 • 2
Energy-Based Transformers are Scalable Learners and Thinkers Paper • 2507.02092 • Published Jul 2, 2025 • 69
AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time Paper • 2505.24863 • Published May 30, 2025 • 97