STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability
Paper • 2606.19236 • Published • 8 •
2
Noah
noahml
AI & ML interests
None yet
Recent Activity
commentedon a paper about 1 hour ago
STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability commentedon a paper about 1 hour ago
A Benchmark and Framework for Evaluating Next Action Predictions in Spreadsheets commentedon a paper about 1 hour ago
LLM-Enabled NWDAF: A Step Toward AI-Native 6G Network IntelligenceOrganizations
None yet
commented 5
papers about 1 hour ago
A Benchmark and Framework for Evaluating Next Action Predictions in Spreadsheets
Paper • 2606.13802 • Published •
2
LLM-Enabled NWDAF: A Step Toward AI-Native 6G Network Intelligence
Paper • 2606.11877 • Published •
2
Morpheus: A Morphology-Aware Neural Tokenizer and Word Embedder for Turkish
Paper • 2606.18717 • Published • 1 •
2
From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning
Paper • 2606.17682 • Published • 11 •
2
commented 5
papers about 8 hours ago
Variable-Width Transformers
Paper • 2606.18246 • Published • 5 •
1
Visual-Seeker: Towards Visual-Native Multimodal Agentic Search via Active Visual Reasoning
Paper • 2606.15231 • Published • 3 •
2
Guava: An Effective and Universal Harness for Embodied Manipulation
Paper • 2606.18363 • Published • 23 •
4
EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts
Paper • 2606.18967 • Published • 16 •
3
SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior
Paper • 2606.18322 • Published • 15 •
3
commented 10
papers 1 day ago
GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?
Paper • 2606.17861 • Published • 41 •
5
Learning from the Self-future: On-policy Self-distillation for dLLMs
Paper • 2606.18195 • Published • 68 •
2
Rethinking the Role of Efficient Attention in Hybrid Architectures
Paper • 2606.15378 • Published • 12 •
2
Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion
Paper • 2606.15236 • Published • 18 •
2
ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining
Paper • 2606.17200 • Published • 42 •
3
MVEB: Massive Video Embedding Benchmark
Paper • 2606.14958 • Published • 13 •
2
You Don't Need Strong Assumptions: Visual Representation Learning via Temporal Differences
Paper • 2606.15956 • Published • 9 •
3
ExpRL: Exploratory RL for LLM Mid-Training
Paper • 2606.17024 • Published • 3 •
2
Text-Vision Co-Instructed Image Editing
Paper • 2606.16767 • Published • 14 •
3
ChLogic: Evaluating Robustness of Logical Reasoning in Chinese Expressions
Paper • 2606.17905 • Published • 6 •
3