OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use Paper • 2610.22200 • Published 7 days ago • 331
History Replays Itself: Unleashing Long-Context Capability in Linear Attention Paper • 2610.15715 • Published 11 days ago • 26
KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization Paper • 2610.14448 • Published 12 days ago • 49
QuadTok: Quadtree Visual Tokenizer for Autoregressive Image Generation Paper • 2610.10497 • Published 15 days ago • 19
Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence Paper • 2610.17656 • Published 9 days ago • 29
CineRecon: Benchmarking Frontier Models for Agentic Cinematic Reconstruction Paper • 2610.16577 • Published 10 days ago • 37
saarvajanik/facebook-opt-6.7b-gqa-ub-16-best-for-KV-cache Text Generation • Updated Jan 28, 2024 • 137 • 6
GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives Paper • 2609.39601 • Published 22 days ago • 314
open-llm-leaderboard-old/details_xformAI__facebook-opt-125m-qcqa-ub-6-best-for-KV-cache Updated Jan 23, 2024 • 623 • 13
One Model to Loop Them All: Elastic Latent Recurrence for Language Models Paper • 2610.12582 • Published 14 days ago • 18
Humanity's Sixth Sense: Benchmarking Intuitive Visual Reasoning in Multimodal Models Paper • 2610.08966 • Published 14 days ago • 26
TokenRouter: Efficient Serving System for Token-Level LLM Routing Paper • 2610.12242 • Published 14 days ago • 144
STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization Paper • 2609.38169 • Published 23 days ago • 132