Native Action-Prior Learning from Videos for World Action Models Paper • 2610.03391 • Published 6 days ago • 87
Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs Paper • 2609.26796 • Published 16 days ago • 37
StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training Paper • 2609.26774 • Published 16 days ago • 56
OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue Paper • 2609.21465 • Published 20 days ago • 151
TeleAntiFraud 2.0: A Refreshable, Profile-Grounded, and Audio-Based Benchmark for Telecom Fraud Detection Paper • 2609.18748 • Published 21 days ago • 10
Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control Paper • 2609.17909 • Published 23 days ago • 47
Building a Production Greek-English Speech Recognizer Paper • 2609.13498 • Published 27 days ago • 9
Generalized Agent Iteration: One Formal Framework for Iterative Policy Improvement and Recursive Self-Improvement Paper • 2609.13406 • Published 27 days ago • 85