Thinking in Frames: How Visual Context and Test-Time Scaling Empower Video Reasoning
Paper β’ 2601.21037 β’ Published β’ 15
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
SeeUPO: Sequence-Level Agentic-RL with Convergence Guarantees
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
DyJiangΒ
authored 3
papers 29 days ago
QJerryΒ
updated 2
models 3 months ago
Paper99Β
updated a
collection 3 months ago
QJerryΒ
published a
model 3 months ago
Paper99Β
updated a
model 3 months ago
QJerryΒ
updated a
collection 3 months ago
Clean old ckpts.
1
#2 opened 3 months ago
by 
QJerry
kongquyuΒ
authored 3
papers 3 months ago
Language-TPP: Integrating Temporal Point Processes with Language Models for Event Analysis
Paper β’ 2502.07139 β’ Published
MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive, and MCP-Augmented Environments
Paper β’ 2512.19432 β’ Published β’ 13
MAI-UI Technical Report: Real-World Centric Foundation GUI Agents
Paper β’ 2512.22047 β’ Published β’ 30
Add metadata, paper/code links, and quick start instructions
π€ 2
#2 opened 4 months ago
by 
nielsr
CleyChenΒ
updated a
collection 4 months ago
DyJiangΒ
authored 3
papers 4 months ago
AutoMLGen: Navigating Fine-Grained Optimization for Coding Agents
Paper β’ 2510.08511 β’ Published
Low-Biased General Annotated Dataset Generation
Paper β’ 2412.10831 β’ Published
Unleashing the Intrinsic Visual Representation Capability of Multimodal Large Language Models
Paper β’ 2512.06281 β’ Published