SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review
Paper • 2607.06065 • Published • 8
Dipankar Sarkar PRO
dipankarsarkar
AI & ML interests
Building the AI-native stack. Agents as infrastructure, safety as architecture, performance as plumbing. I publish the receipts: papers, datasets, demos.
Recent Activity
repliedto sergiopaniego's post 6 days ago
Frontier models use distillation as a step of their post-training pipelines.
In 2026 it has three jobs: compress a big model into a small one, merge RL experts into a single model, and let a model teach itself.
I wrote up which frontier models use each one and how: https://huggingface.co/blog/sergiopaniego/distillation-2026
It pairs with Class 2 of the Training an Agent series Ben and I are doing, where we teach these techniques hands-on with TRL! reacted to sergiopaniego's post with 🔥 6 days ago
Frontier models use distillation as a step of their post-training pipelines.
In 2026 it has three jobs: compress a big model into a small one, merge RL experts into a single model, and let a model teach itself.
I wrote up which frontier models use each one and how: https://huggingface.co/blog/sergiopaniego/distillation-2026
It pairs with Class 2 of the Training an Agent series Ben and I are doing, where we teach these techniques hands-on with TRL! upvoted a paper 6 days ago
SWE-Review: Closing the Loop on Issue Resolution with Agentic Code ReviewOrganizations
upvoted 4
papers 6 days ago
TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training
Paper • 2607.05804 • Published • 18
Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity
Paper • 2607.07386 • Published • 11
Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning
Paper • 2607.07508 • Published • 22
upvoted 3
papers 7 days ago
When Classic Cache Policies Fail: Learning-Augmented Replacement for Semantic Retrieval Buffers
Paper • 2607.00394 • Published • 6
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
Paper • 2607.05147 • Published • 33
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling
Paper • 2607.02980 • Published • 75
upvoted 13
papers 8 days ago
ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog
Paper • 2607.04438 • Published • 61
SeKV: Resolution-Adaptive KV Cache with Hierarchical Semantic Memory for Long-Context LLM Inference
Paper • 2606.31145 • Published • 11
Multi-Turn Agentic Scientific Literature Search via Workflow Induction
Paper • 2607.00597 • Published • 28
ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes
Paper • 2607.04439 • Published • 54
EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments
Paper • 2607.05155 • Published • 17
KVpop -- Key-Value Cache Compression with Predictive Online Pruning
Paper • 2607.05061 • Published • 21
Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction
Paper • 2607.01764 • Published • 8
GORGO: Online Tuning for Cross-Region Network-Aware LLM Serving
Paper • 2602.11688 • Published • 7
dOPSD: On-Policy Self-Distillation for Diffusion Language Models
Paper • 2607.04428 • Published • 17
UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning
Paper • 2607.04425 • Published • 70
PraMem: Practice-derived Experiential Memory for Long-horizon Behavior Prediction
Paper • 2607.02881 • Published • 9
LLM-as-a-Verifier: A General-Purpose Verification Framework
Paper • 2607.05391 • Published • 14
Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification
Paper • 2607.01793 • Published • 7