Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm Paper • 2511.04570 • Published 7 days ago • 187
Kimi Linear: An Expressive, Efficient Attention Architecture Paper • 2510.26692 • Published 14 days ago • 105
JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence Paper • 2510.23538 • Published 17 days ago • 95
DeepAgent: A General Reasoning Agent with Scalable Toolsets Paper • 2510.21618 • Published 20 days ago • 95
AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders Paper • 2510.19779 • Published 22 days ago • 58
LightMem: Lightweight and Efficient Memory-Augmented Generation Paper • 2510.18866 • Published 23 days ago • 108
A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning Paper • 2510.15444 • Published 28 days ago • 145
Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples Paper • 2510.07192 • Published Oct 8 • 5
Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation Paper • 2510.08673 • Published Oct 9 • 121
Cache-to-Cache: Direct Semantic Communication Between Large Language Models Paper • 2510.03215 • Published Oct 3 • 96
MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use Paper • 2509.24002 • Published Sep 28 • 170