Partially Correlated Verifier Cascades in LLM Harnesses: Concave Log-Odds, Polynomial Reliability, and Blind-Spot Ceilings
Paper • 2607.13918 • Published • 2
S5lpnqwp7
s5lpnqwp7
·
AI & ML interests
None yet
Recent Activity
liked a dataset 4 days ago
own2pwn-fr/ctfhoard-corpus liked a model 7 days ago
majentik/gemma-4-12B-it-TurboQuant-MLX-NVFP4Organizations
None yet
upvoted a paper about 8 hours ago
upvoted a paper 8 days ago
upvoted 5
papers about 2 months ago
Domain-Specific Data Synthesis for LLMs via Minimal Sufficient Representation Learning
Paper • 2605.30039 • Published • 20
On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters
Paper • 2606.02437 • Published • 240
Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion
Paper • 2605.31170 • Published • 12
Beyond Final Answers: Auditing Trajectory-Level Hallucinations in Multi-Agent Industrial Workflows
Paper • 2605.24219 • Published • 9
OpenComputer: Verifiable Software Worlds for Computer-Use Agents
Paper • 2605.19769 • Published • 88
upvoted a paper 2 months ago
upvoted 2
papers 3 months ago
upvoted 4
papers 4 months ago
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning
Paper • 2604.02721 • Published • 639
DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models
Paper • 2603.26164 • Published • 365
Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models
Paper • 2603.25716 • Published • 157
Demystifing Video Reasoning
Paper • 2603.16870 • Published • 373