Itai Shapira

itai-sh's activity

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

upvoted a paper about 22 hours ago

VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding

Paper • 2611.08449 • Published 6 days ago • 112

upvoted a paper 1 day ago

What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents?

Paper • 2611.06483 • Published 6 days ago • 39

upvoted a paper 2 days ago

Turns Matter: Advancing Streaming Video RL via Turn-Level Credit

Paper • 2611.06728 • Published 7 days ago • 70

upvoted a paper 3 days ago

SpecOPD: Branch-Parallel On-Policy Distillation for Speculative Decoding

Paper • 2611.02846 • Published 9 days ago • 16

upvoted 3 papers 5 days ago

FlowTranslator: Training-Free In-Image Machine Translation with Flow-Based Editing

Paper • 2611.04303 • Published 8 days ago • 13

SpecPilot: Autonomous Algorithm Discovery and Systems Optimization for Speculative Decoding

Paper • 2611.02501 • Published 9 days ago • 21

MAServeBench: Benchmarking Multi-Agent LLM Serving Systems with Hierarchical Collaboration Workloads

Paper • 2610.40293 • Published 13 days ago • 11

upvoted a paper 6 days ago

REA: A Routed Embodied Agent Runtime for Asynchronous Brain-Cerebellum Control

Paper • 2610.42053 • Published 11 days ago • 17

upvoted 2 papers 8 days ago

PhysInsert: Physically Plausible Object Insertion with Geometric Priors and Bidirectional Object-Scene Interactions

Paper • 2610.40453 • Published 13 days ago • 14

Timestral

Paper • 2610.37585 • Published 15 days ago • 15

upvoted 2 papers 10 days ago

Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success

Paper • 2610.31670 • Published 19 days ago • 8

Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes

Paper • 2610.32749 • Published 19 days ago • 29

upvoted a paper 11 days ago

Cross-modal Steering Vectors Exist Across Both Image and Text Generation

Paper • 2610.36269 • Published 16 days ago • 11

upvoted a paper 13 days ago

Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL

Paper • 2610.33512 • Published 18 days ago • 35

upvoted a paper 14 days ago

RSIHub: A Composable Framework for Agent-Evolution Methods

Paper • 2610.32253 • Published 19 days ago • 44

upvoted a paper 15 days ago

MolLean: A Process-Verifiable Language for Chemical Reasoning

Paper • 2610.20459 • Published 28 days ago • 11

upvoted a paper 16 days ago

Tree-Aware Posterior Distillation for Long-Horizon Agentic Reinforcement Learning

Paper • 2610.23181 • Published 26 days ago • 44

upvoted a paper 17 days ago

Right Screen, Wrong Transition: World Models as Verifiers for GUI Agents

Paper • 2610.11942 • Published Oct 8 • 9

upvoted 2 papers 18 days ago

Which Agent's Skill Should Change? Group-Relative Credit Assignment for Evolving Multi-Agent Teams

Paper • 2610.27227 • Published 23 days ago • 11

Focused Omni-Modal GUI Agents

Paper • 2610.26203 • Published 23 days ago • 32