Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
Paper • 2408.03314 • Published • 67
Research Papers
-
-
TAG: A Decentralized Framework for Multi-Agent Hierarchical Reinforcement Learning
Paper • 2502.15425 • Published • 9 -
EgoLife: Towards Egocentric Life Assistant
Paper • 2503.03803 • Published • 47 -
Visual-RFT: Visual Reinforcement Fine-Tuning
Paper • 2503.01785 • Published • 86 -
AlphaMaze: Enhancing Large Language Models' Spatial Intelligence via GRPO
Paper • 2502.14669 • Published • 15 -
Qwen2.5-Omni Technical Report
Paper • 2503.20215 • Published • 174 -
Husky: A Unified, Open-Source Language Agent for Multi-Step Reasoning
Paper • 2406.06469 • Published • 29 -
Cognitive Kernel: An Open-source Agent System towards Generalist Autopilots
Paper • 2409.10277 • Published • 1 -
ByteDance-Seed/UI-TARS-1.5-7B
Image-Text-to-Text • 8B • Updated • 900k • • 584 -
Magma: A Foundation Model for Multimodal AI Agents
Paper • 2502.13130 • Published • 58 -
Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs
Paper • 2504.17432 • Published • 41 -
togethercomputer/StripedHyena-Nous-7B
Text Generation • 8B • Updated • 272 • 144 -
ARM: Adaptive Reasoning Model
Paper • 2505.20258 • Published • 45 -
SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
Paper • 2506.01844 • Published • 165 -
ATLAS: Learning to Optimally Memorize the Context at Test Time
Paper • 2505.23735 • Published • 23 -
Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos
Paper • 2507.15597 • Published • 34 -
DINOv3
Paper • 2508.10104 • Published • 315 -
Beyond the Exploration-Exploitation Trade-off: A Hidden State Approach for LLM Reasoning in RLVR
Paper • 2509.23808 • Published • 47 -
Reactive Transformer (RxT) -- Stateful Real-Time Processing for Event-Driven Reactive Language Models
Paper • 2510.03561 • Published • 25 -
Less is More: Recursive Reasoning with Tiny Networks
Paper • 2510.04871 • Published • 519 -
moonshotai/Kimi-Linear-48B-A3B-Instruct
Text Generation • 49B • Updated • 106k • • 573 -
MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation
Paper • 2511.09611 • Published • 72 -
UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity
Paper • 2511.13714 • Published • 13 -
Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning
Paper • 2511.14460 • Published • 22 -
Titans: Learning to Memorize at Test Time
Paper • 2501.00663 • Published • 31 -
Universal Transformers
Paper • 1807.03819 • Published • 2 -
Metis: Memory Foundation Model
Paper • 2607.26760 • Published • 270