LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget
Paper • 2607.14952 • Published • 206
宮本美亜 (Miyamoto Mia)
mia-97
AI & ML interests
None yet
Recent Activity
liked a dataset 5 days ago
cstr/crispasr-kaggle-progress liked a dataset 11 days ago
cais/mmlu liked a dataset 15 days ago
bigcode/the-stackOrganizations
None yet
upvoted a paper 17 days ago
upvoted a paper 19 days ago
upvoted 2
papers about 1 month ago
upvoted 5
papers 2 months ago
Rethinking VLM Representation for VLA Initialization
Paper • 2605.25802 • Published • 15
EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation
Paper • 2605.23271 • Published • 82
Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding
Paper • 2605.20104 • Published • 7
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
Paper • 2605.11609 • Published • 196
Agent Bazaar: Enabling Economic Alignment in Multi-Agent Marketplaces
Paper • 2605.17698 • Published • 6
upvoted a paper 3 months ago
upvoted 3
papers 4 months ago
Structural Graph Probing of Vision-Language Models
Paper • 2603.27070 • Published • 6
CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence
Paper • 2603.28032 • Published • 344
The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamics
Paper • 2603.14375 • Published • 20
upvoted 5
papers 5 months ago
InCoder-32B: Code Foundation Model for Industrial Scenarios
Paper • 2603.16790 • Published • 312
DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval
Paper • 2603.04743 • Published • 54
Heterogeneous Agent Collaborative Reinforcement Learning
Paper • 2603.02604 • Published • 199
A Very Big Video Reasoning Suite
Paper • 2602.20159 • Published • 526
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
Paper • 2602.10693 • Published • 221
upvoted 2
papers 6 months ago