OpenESM: Energy-Steered Models Are Scalable Foundation Learners
Paper • 2610.33005 • Published • 6
Yury Panikov
panikov
AI & ML interests
None yet
Recent Activity
upvoted a paper about 16 hours ago
OpenESM: Energy-Steered Models Are Scalable Foundation Learners upvoted a paper about 16 hours ago
ThinkBit: Search Codewords, Recalibrate Scales, Select by Reasoning upvoted a paper about 16 hours ago
Gluing Local Contexts into Global Meaning: A Sheaf-Theoretic Decomposition of Transformer RepresentationsOrganizations
None yet
upvoted 20
papers about 16 hours ago
ThinkBit: Search Codewords, Recalibrate Scales, Select by Reasoning
Paper • 2610.34886 • Published • 6
Gluing Local Contexts into Global Meaning: A Sheaf-Theoretic Decomposition of Transformer Representations
Paper • 2610.17117 • Published • 6
Did the Model Use That? Counterfactual Training Boosts Self-Attribution in Language Models
Paper • 2610.35295 • Published • 7
Intrinsic Goals for Autonomous Agents: Hierarchical Exploration Captures Future Volitional Action in Drosophila
Paper • 2610.34638 • Published • 8
Semantic Concept Steering Breaks the Explanation Drift Loop in Continual Learning
Paper • 2610.33877 • Published • 8
Constrained Decoding: Harmful or Beneficial? Revisiting Its Impact on LLM Performance
Paper • 2610.35328 • Published • 10
Rethinking Verification in Agent Harnesses
Paper • 2610.34577 • Published • 10
Skill^{infty}: Recursive Self-Improvement for Agent Skill Optimization
Paper • 2610.35434 • Published • 12
CRM-Agent-Bench: Benchmarking Tool-Using Agents in Stateful Enterprise Environments
Paper • 2610.32004 • Published • 13
Beyond Benchmarks: Can Small Open-Weight Models Get Real Coding Work Done?
Paper • 2610.34241 • Published • 13
Joint or Per-Option? Compact Encoders for Closed-Set Decisions from 17 Million to 1 Billion Parameters
Paper • 2610.30970 • Published • 13
DialFork: Going Beyond Factuality to Evaluate Procedural Hallucination in Conversational Agents
Paper • 2610.21561 • Published • 13
Nested Sparsity for Scalable Pretraining and Continual Learning
Paper • 2610.31818 • Published • 15
Novel or Not? PatEx-Gym: Agentic Prior-Art Search for Novelty Assessment in Patent Examination
Paper • 2610.33503 • Published • 14
AgentProofBench: Benchmarking Reusable Verifiers for Web Agents
Paper • 2610.34634 • Published • 16
ParetoRSI-Gym: Can AI Agents Improve Language Models Across Multiple Domains?
Paper • 2610.34386 • Published • 16
Steering Black-Box Large Language Model Agents with Pitfall Anticipation World Model
Paper • 2610.29139 • Published • 16
ReGE: Stronger Agents through Experience Synthesis
Paper • 2610.33861 • Published • 18
Thinking-in-Bets at Test Time Reduces Sycophantic Revisions in LLM Agents
Paper • 2610.34654 • Published • 19