Athanor: An Agent-Native System for Autonomous Post-Training Research
Paper • 2610.21055 • Published • 17
Finn Reyes
finnreyes
AI & ML interests
combinatorial optimization, test-time compute
Recent Activity
upvoted a paper about 10 hours ago
Athanor: An Agent-Native System for Autonomous Post-Training Research upvoted a paper about 10 hours ago
Virtual Head Attention upvoted a paper about 10 hours ago
MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning EngineeringOrganizations
None yet
upvoted 7
papers about 10 hours ago
Virtual Head Attention
Paper • 2610.17959 • Published • 25
MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering
Paper • 2610.22344 • Published • 29
Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation
Paper • 2610.21601 • Published • 223
SCOPE: Semantic Bounded Credit Optimization for Prompt Engineering in Text-to-image Generation
Paper • 2610.22264 • Published • 45
EAU: Environment-Agent-User Co-evolution for Training User-Centric Agents
Paper • 2610.16523 • Published • 20
Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation
Paper • 2610.29989 • Published • 166
upvoted 7
papers 2 days ago
PhysLDM: Latent Diffusion for High-Fidelity Deformable Simulation
Paper • 2610.07609 • Published • 9
Large Flow Language Models
Paper • 2610.28559 • Published • 23
EdgeKernelBench: Unified LLM-Driven Kernel Generation for Edge Backends
Paper • 2610.24648 • Published • 16
On the Fragility of Tasks under Composition: Implicit Budgeting in Language Models
Paper • 2610.27190 • Published • 11
FlowState: Execution State as Memory for Long-Horizon LLM Agents
Paper • 2609.34565 • Published • 24
More Memory, Worse Agents: Error Reproduction and Anti-Persistence in LLM Agents
Paper • 2610.27406 • Published • 16
Correction Training for Diffusion Models
Paper • 2610.14136 • Published • 47
upvoted 4
papers 3 days ago
OR-License: Evaluating LLM Agents as Real-World Operations Research Practitioners
Paper • 2610.24087 • Published • 51
Interlock: From Local Correctness to Task Completion in Long-Horizon Agents
Paper • 2610.19686 • Published • 49
BlenderWorld: Benchmarking Visual Agents for 3D Creation from Real-World References
Paper • 2610.23986 • Published • 39
RoAR-VAE: Improving Latent Diffusability through Robust Prediction
Paper • 2610.26216 • Published • 41
upvoted 2
papers 4 days ago