FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience
Paper • 2609.03241 • Published • 91
Xin Liu
xinliuthu
AI & ML interests
Natural language processing, text classification, language model pretraining, semantic similarity
Recent Activity
upvoted a paper about 6 hours ago
FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience upvoted a paper about 22 hours ago
Unifying Conformal Language Tasks with In-Context Ensembles upvoted a paper about 22 hours ago
Unlocking Lossless Speedups in LLMs via Discrete DiffusionOrganizations
None yet
upvoted a paper about 6 hours ago
upvoted 2
papers about 22 hours ago
upvoted a paper 3 days ago
upvoted 2
papers 4 days ago
upvoted 3
papers 5 days ago
Blind Men and the Elephant: Probing the Epistemic Myopia of LLMs under Long-Tail Divergent Knowledge
Paper • 2608.28478 • Published • 20
Scaffolding Foundation Models into Physical-World Agents Pushes the Frontier of Long-Horizon Navigation
Paper • 2608.30396 • Published • 12
UI-Venus-2 Technical Report
Paper • 2609.00028 • Published • 64
upvoted a paper 6 days ago
upvoted 4
papers 7 days ago
EM^2Mem: Event-Centric Multimodal Memory for Large Language Models
Paper • 2609.00551 • Published • 14
Hi-Q: Hierarchical Evidence-guided Query Refinement for Multi-Hop Question Answering
Paper • 2608.30468 • Published • 37
Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving
Paper • 2609.00111 • Published • 379
StudentSim: Training LLM-based Student Simulators
Paper • 2609.01591 • Published • 486