FRAUDSkill: Structured Frozen-Weight Skill Optimization for Audio Anti-Fraud Detection Paper • 2609.18766 • Published 12 days ago • 7
OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue Paper • 2609.21465 • Published 10 days ago • 149
Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs Paper • 2609.26796 • Published 6 days ago • 36
Harness-Zero: Harness Distillation via Agent-as-Harness Paper • 2609.24974 • Published 7 days ago • 37
MLLMs Hallucinate when Information Distribution Drifts in Synergy Heads Paper • 2609.09206 • Published 23 days ago • 11
When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation Paper • 2609.20511 • Published 11 days ago • 110
Gaze as Evidence for Common Grounding: A Cross-Corpus Analysis of MapTask and MUNDEX Paper • 2609.18011 • Published 12 days ago • 30
ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents Paper • 2609.17523 • Published 13 days ago • 30
ReactHuman: A Physics-Grounded Benchmark for Human-Like Reactive Decision-Making in Embodied Multimodal LLMs Paper • 2609.10895 • Published 19 days ago • 54
Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation Paper • 2609.11115 • Published 18 days ago • 172
NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction Paper • 2609.10715 • Published 19 days ago • 329