ChatPaper
Trending AI Papers
The papers AI researchers worldwide upvoted this week, explained in plain language
1
FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation
š„ 112
2026-10-27
Deep read
arXiv
2
Advances in Agentic Computer Graphics
š„ 110
2026-11-01
Deep read
arXiv
3
Wave Forcing: Towards Speed-of-Light Streaming Video Generation
š„ 103
2026-10-31
Deep read
arXiv
4
CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements
š„ 92
2026-11-02
Deep read
arXiv
5
VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding
š„ 89
2026-11-05
Deep read
arXiv
6
CoworkOS:Scaling Agent Coworkers for Real-world Automation
š„ 88
2026-11-02
Deep read
arXiv
7
R^2Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization Loop
š„ 88
2026-10-22
Deep read
arXiv
8
Route Anything: A Study of Model and Policy Routing for General-Purpose AI Systems
š„ 84
2026-11-03
Deep read
arXiv
9
Turns Matter: Advancing Streaming Video RL via Turn-Level Credit
š„ 80
2026-11-04
Deep read
arXiv
10
Video Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self-Improvement
š„ 69
2026-10-29
Deep read
arXiv
11
Words Caught in the Heart: Simulating Person-Specific Expression for Self-Opaque Clients in Psychotherapy
š„ 67
2026-10-31
Deep read
arXiv
12
Think Less, Locally: Local Preference Learning for Reasoning Compression
š„ 65
2026-11-03
Deep read
arXiv
13
MoviEdit: Long-form Multi-Shot Video Editing Made Easy
š„ 61
2026-11-02
Deep read
arXiv
14
From Pixels to Actions - Towards Native Vision-Language-Action Policies
š„ 56
2026-11-04
Deep read
arXiv
15
Harness-S: Learning from Sibling Harnesses for Generalizable Agent Training
š„ 54
2026-11-03
Deep read
arXiv
16
Does Scaling Toward AGI Depend on What System-1 Lets System-2 Execute?
š„ 53
2026-10-29
Deep read
arXiv
17
Behind Video Generation: Observations and Insights on Multimodal Understanding from Kling
š„ 51
2026-11-03
Deep read
arXiv
18
DreamX: Video Diffusion Model is a Universal Latent Action Learner
š„ 50
2026-11-03
Deep read
arXiv
19
Random Is Almost Enough? Stable and Low-Cost Benchmark Compression via BestRand
š„ 50
2026-10-31
Deep read
arXiv
20
SLA: Scaling Spatial-Language-Action Model via Continual Pre-training
š„ 48
2026-11-05
Deep read
arXiv