James Johnson

Kestrel-Evan's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 13 days ago

MixTok: Adaptive Visual Tokenization with Global 1D Tokens and Sparse 2D Refinement

Paper • 2610.13181 • Published 16 days ago • 15

upvoted a paper 14 days ago

Can AI Agents Make Open-Ended Scientific Discovery? Evidence from Station

Paper • 2610.08927 • Published 19 days ago • 13

upvoted 5 papers about 1 month ago

EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents

Paper • 2609.17632 • Published Sep 15 • 45

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published Sep 7 • 371

Atria Dawn: The Dawn of Agentic Superintelligence

Paper • 2609.15818 • Published Sep 14 • 376

Studying Image Tokenizers as Visual Languages in Unified Multimodal Models

Paper • 2609.09143 • Published Sep 8 • 28

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published Aug 29 • 483

upvoted 4 papers about 2 months ago

Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions

Paper • 2608.29109 • Published Aug 29 • 17

Procedural Graphs: Self-Evolving Execution Structures for LLM Agents

Paper • 2609.09153 • Published Sep 8 • 43

FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow

Paper • 2609.03563 • Published Sep 3 • 18

Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training

Paper • 2608.26730 • Published Aug 27 • 133

upvoted 4 papers 2 months ago

SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation

Paper • 2608.17426 • Published Aug 18 • 160

Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination

Paper • 2608.14391 • Published Aug 14 • 286

An AI4AI Framework for Visual Token Pruning

Paper • 2608.07193 • Published Aug 7 • 15

OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution

Paper • 2608.00677 • Published Aug 1 • 263

upvoted 2 papers 3 months ago

Consistency-Driven Co-Evolution for Self-Supervised Cross-Representation Learning

Paper • 2608.04926 • Published Aug 5 • 9

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks

Paper • 2608.02023 • Published Aug 3 • 159