Reasoning Shift: How Context Silently Shortens LLM Reasoning
Paper • 2604.01161 • Published • 22 •
2
Avi
avahal
AI & ML interests
LLMs
Recent Activity
commentedon a paper about 6 hours ago
Reasoning Shift: How Context Silently Shortens LLM Reasoning commentedon a paper about 6 hours ago
QuitoBench: A High-Quality Open Time Series Forecasting Benchmark commentedon a paper about 6 hours ago
Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent VerificationOrganizations
None yet
commented 7
papers about 6 hours ago
QuitoBench: A High-Quality Open Time Series Forecasting Benchmark
Paper • 2603.26017 • Published • 25 •
2
Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification
Paper • 2603.26648 • Published • 32 •
2
ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners?
Paper • 2603.25823 • Published • 36 •
2
Terminal Agents Suffice for Enterprise Automation
Paper • 2604.00073 • Published • 65 •
2
MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome
Paper • 2603.28407 • Published • 52 •
2
ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers
Paper • 2603.24414 • Published • 164 •
2
commented 11
papers 1 day ago
Lingshu-Cell: A generative cellular world model for transcriptome modeling toward virtual cells
Paper • 2603.25240 • Published • 73 •
4
CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence
Paper • 2603.28032 • Published • 290 •
4
LongCat-Next: Lexicalizing Modalities as Discrete Tokens
Paper • 2603.27538 • Published • 121 •
4
FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization
Paper • 2603.19835 • Published • 302 •
7
Gen-Searcher: Reinforcing Agentic Search for Image Generation
Paper • 2603.28767 • Published • 51 •
3
Towards a Medical AI Scientist
Paper • 2603.28589 • Published • 81 •
3
TAPS: Task Aware Proposal Distributions for Speculative Sampling
Paper • 2603.27027 • Published • 136 •
4
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Paper • 2603.25158 • Published • 44 •
14
PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference
Paper • 2603.25730 • Published • 46 •
3
ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling
Paper • 2603.25746 • Published • 150 •
6
Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models
Paper • 2603.25716 • Published • 147 •
4
commented 2
papers 7 days ago