ChatPaper
Trending AI Papers
The papers AI researchers worldwide upvoted this week, explained in plain language
1
Envisioning Agentic Robotics: A New Era of Robotic Systems
🔥 107
2026-11-13
Deep read
arXiv
2
Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agent
🔥 87
2026-11-13
Deep read
arXiv
3
Sage S2.1 Flash Technical Report
🔥 85
2026-11-16
Deep read
arXiv
4
VibePrevisBench: Evaluating Agentic Coding for 4D Scene Generation in Blender
🔥 83
2026-11-11
Deep read
arXiv
5
Tree-Ising: Repairing Language Models with Bit-Level Ising Edits
🔥 75
2026-11-10
Deep read
arXiv
6
SO-Arena: Benchmarking the Capability Spectrum and Reliability of System One Models
🔥 73
2026-11-11
Deep read
arXiv
7
K2-Horizon: A Frontier Fleet of Open Source Language Models
🔥 72
2026-11-16
Deep read
arXiv
8
AllocFlow: End-to-End Portfolio Trading Action Generation from Raw Market Data
🔥 67
2026-11-15
Deep read
arXiv
9
Few-Step Streaming Video Generation via Condition Shifting
🔥 66
2026-11-10
Deep read
arXiv
10
World In-Context Learning for Agentic Robot Manipulation
🔥 64
2026-11-09
Deep read
arXiv
11
InclusionMed: Benchmarking AI for Inclusive Healthcare
🔥 62
2026-11-16
Deep read
arXiv
12
SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt Injection
🔥 51
2026-11-04
Deep read
arXiv
13
Don't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents
🔥 48
2026-11-10
Deep read
arXiv
14
BirdDreams: Joint Perspective and BEV Video Generation for a Plausible, Reactive Driving World Model
🔥 46
2026-11-10
Deep read
arXiv
15
MIRIX-2.0: Multi-Agent Memory System
🔥 45
2026-11-09
Deep read
arXiv
16
SWE-CoWork: Benchmarking Coding Agents as Digital Employees in Organizations
🔥 44
2026-11-15
Deep read
arXiv
17
PhysLoop: Harnessing LLMs' Physics Awareness for Self-Improving Video Generation Models
🔥 42
2026-11-12
Deep read
arXiv
18
ScaleVLA: Scaling Vision-Language-Action Models to 552 Billion Parameters
🔥 41
2026-11-16
Deep read
arXiv
19
G-STAR: Group-Scaled Token Capacity for Deeply Compressed Autoregressive Generation
🔥 40
2026-11-08
Deep read
arXiv
20
Scaling Mathematical Proof Supervision from Structured Textbooks
🔥 39
2026-10-29
Deep read
arXiv