pith. sign in

Linfeng Zhang

Identifiers

  • name variant Linfeng Zhang 0.60 · backfill

Papers (48)

  1. AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security cs.AI · 2026 · author #25
  2. Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding cs.CL · 2026 · author #6
  3. The Missing Piece in Pre-trained Model Evaluation: Reward-Guided Decoding Unlocks Task-Oriented Behavior Without Parameter Updates cs.CL · 2026 · author #8
  4. Dynamic Video Generation: Shaping Video Generation Across Time and Space cs.CV · 2026 · author #8
  5. FlexDraft: Flexible Speculative Decoding via Attention Tuning and Bonus-Guided Calibration cs.CL · 2026 · author #8
  6. Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion cs.CV · 2026 · author #11
  7. Elastic-dLLM: Position Preserving Context Compression and Augmentation of Diffusion LLMs cs.LG · 2026 · author #4
  8. Entropy-Gradient Inversion: Moving Toward Internal Mechanism of Large Reasoning Models cs.AI · 2026 · author #4
  9. DISA: Offline Importance Sampling for Distribution-Matching LLM-RL cs.LG · 2026 · author #12
  10. Respecting Self-Uncertainty in On-Policy Self-Distillation for Efficient LLM Reasoning cs.AI · 2026 · author #5
  11. Attributing Emergence in Million-Agent Systems cs.AI · 2026 · author #5
  12. DataMaster: Data-Centric Autonomous AI Research cs.LG · 2026 · author #13
  13. EvoStreaming: Your Offline Video Model Is a Natively Streaming Assistant cs.CV · 2026 · author #8
  14. ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models cs.CV · 2026 · author #5
  15. AgentSlimming: Towards Efficient and Cost-Aware Multi-Agent Systems cs.LG · 2026 · author #6
  16. SpecEdit: Training-Free Acceleration for Diffusion based Image Editing via Semantic Locking cs.CV · 2026 · author #12
  17. Reasoning emerges from constrained inference manifolds in large language models cs.LG · 2026 · author #3
  18. Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models cs.CV · 2026 · author #9
  19. HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models cs.SD · 2026 · author #10
  20. Stability Implies Redundancy: Delta Attention Selective Halting for Efficient Long-Context Prefilling cs.AI · 2026 · author #7
  21. EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale cs.AI · 2026 · author #20
  22. ProtoCycle: Reflective Tool-Augmented Planning for Text-Guided Protein Design q-bio.QM · 2026 · author #8
  23. PRL-Bench: A Comprehensive Benchmark Evaluating LLMs' Capabilities in Frontier Physics Research cs.LG · 2026 · author #18
  24. StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding cs.CV · 2026 · author #9
  25. AnomalyAgent: Agentic Industrial Anomaly Synthesis via Tool-Augmented Reinforcement Learning cs.CV · 2026 · author #6
  26. AudioKV: KV Cache Eviction in Efficient Large Audio Language Models cs.SD · 2026 · author #9
  27. IndustryCode: A Benchmark for Industry Code Generation cs.SE · 2026 · author #10
  28. Systematically Improvable Numerical Atomic Orbital Basis Using Contracted Truncated Spherical Waves physics.chem-ph · 2026 · author #3
  29. Draft-Refine-Optimize: Self-Evolved Learning for Natural Language to MongoDB Query Generation cs.DB · 2026 · author #4
  30. LESA: Learnable Stage-Aware Predictors for Diffusion Model Acceleration cs.CV · 2026 · author #6
  31. DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching cs.CV · 2026 · author #10
  32. AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security cs.AI · 2026 · author #35
  33. Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods cs.CV · 2025 · author #12
  34. Emergent Slow Thinking in LLMs as Inverse Tree Freezing cs.AI · 2025 · author #5
  35. MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing cs.CV · 2025 · author #42
  36. MemOS: A Memory OS for AI System cs.CL · 2025 · author #28
  37. SCAN: A Scalable Neural Networks Framework Towards Compact and Efficient Models cs.LG · 2019 · author #1
  38. Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation cs.LG · 2019 · author #1
  39. Deep learning inter-atomic potential model for accurate irradiation damage simulations physics.comp-ph · 2019 · author #3
  40. Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation physics.comp-ph · 2018 · author #1
  41. Monge-Amp\`ere Flow for Generative Modeling cs.LG · 2018 · author #1
  42. StructADMM: A Systematic, High-Efficiency Framework of Structured Weight Pruning for DNNs cs.NE · 2018 · author #6
  43. Adaptive coupling of a deep neural network potential to a classical force field physics.chem-ph · 2018 · author #1
  44. DeePCG: constructing coarse-grained models via deep neural networks physics.chem-ph · 2018 · author #1
  45. DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics physics.comp-ph · 2017 · author #2
  46. Reinforced dynamics for enhanced sampling in large atomic and molecular systems physics.chem-ph · 2017 · author #1
  47. Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics physics.comp-ph · 2017 · author #1
  48. Global $\alpha$-decay study based on the mass table of the relativistic continuum Hartree-Bogoliubov theory nucl-th · 2015 · author #1

Mentions

  • 2605.29801 #25 · arxiv_oai · confidence 0.70 Linfeng Zhang
  • 2605.29707 #6 · arxiv_oai · confidence 0.70 Linfeng Zhang
  • 2605.28020 #8 · arxiv_oai · confidence 0.70 Linfeng Zhang
  • 2602.20497 #6 · arxiv_oai · confidence 0.70 Linfeng Zhang
  • 2604.18103 #7 · arxiv_oai · confidence 0.70 Linfeng Zhang
  • 2605.21042 #8 · arxiv_oai · confidence 0.70 Linfeng Zhang
  • 2605.20022 #8 · arxiv_oai · confidence 0.70 Linfeng Zhang
  • 2605.18346 #11 · arxiv_oai · confidence 0.70 Linfeng Zhang
  • 2605.18165 #4 · arxiv_oai · confidence 0.70 Linfeng Zhang
  • 2605.17770 #4 · arxiv_oai · confidence 0.70 Linfeng Zhang
  • 2605.17295 #12 · arxiv_oai · confidence 0.70 Linfeng Zhang
  • 2509.22186 #42 · arxiv_oai · confidence 0.70 Linfeng Zhang

Frequent Coauthors