pith. sign in

Junjie Wang

Identifiers

  • name variant Junjie Wang 0.60 · backfill

Papers (48)

  1. SlimSearcher: Training Efficiency-Aware Web Agents via Adaptive Reward Gating cs.LG · 2026 · author #2
  2. From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws cs.SE · 2026 · author #2
  3. WebRISE: Requirement-Induced State Evaluation for MLLM-Generated Web Artifacts cs.CL · 2026 · author #3
  4. Identifying sensitivity-dominant parameters via active subspaces in reduced-order modeling of fluid dynamics physics.flu-dyn · 2026 · author #4
  5. Decoupled Residual Quantization for Robust Semantic IDs in Recommendation cs.IR · 2026 · author #2
  6. Differentiable Particle-Mesh Ewald with Cartesian Tensor Message Passing for Learning Long-Range Electrostatics and Dipole Response physics.comp-ph · 2026 · author #2
  7. Internalize the Temperature: On-Policy Self-Distillation as Policy Reheater for Reinforcement Learning cs.CL · 2026 · author #5
  8. Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO cs.LG · 2026 · author #8
  9. Benchmarking and Evolving Reason-Reflect-Rectify for Reflective Visual Generation cs.CV · 2026 · author #1
  10. EPIC: Abstraction and Polymorphism of In-Network Collectives on Ethernet cs.DC · 2026 · author #26
  11. AgentSteerTTS: A Multi-Agent Closed-Loop Framework for Composite-Instruction Text-to-Speech cs.CV · 2026 · author #5
  12. Think-with-Rubrics: From External Evaluator to Internal Reasoning Guidance cs.CL · 2026 · author #3
  13. OrchJail: Jailbreaking Tool-Calling Text-to-Image Agents by Orchestration-Guided Fuzzing cs.MA · 2026 · author #3
  14. Velocity-Space 3D Asset Editing cs.GR · 2026 · author #5
  15. Where Did It Go Wrong? Capability-Oriented Failure Attribution for Vision-and-Language Navigation Agents cs.MA · 2026 · author #3
  16. Seeing the Whole Elephant: A Benchmark for Failure Attribution in LLM-based Multi-Agent Systems cs.MA · 2026 · author #2
  17. Amorphous Nanoconfinement Enables Self-sustaining Sabatier Reaction at Ambient Conditions cond-mat.mtrl-sci · 2026 · author #10
  18. Interplay of Flat-band and Anderson localizations in disordered moire superlattices cond-mat.dis-nn · 2026 · author #3
  19. From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution cs.SE · 2026 · author #1
  20. NEPMaker: Active learning of neuroevolution machine learning potential for large cells physics.comp-ph · 2026 · author #1
  21. Mapping generative AI use in the human brain: divergent neural, academic, and mental health profiles of functional versus socio emotional AI use q-bio.NC · 2026 · author #1
  22. Linear-Nonlinear Fusion Neural Operator for Partial Differential Equations cs.LG · 2026 · author #2
  23. WebClipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruning cs.AI · 2026 · author #1
  24. EvoEGF-Mol: Evolving Exponential Geodesic Flow for Structure-based Drug Design cs.LG · 2026 · author #2
  25. ProFit: Leveraging High-Value Signals in SFT via Probability-Guided Token Selection cs.CL · 2026 · author #5
  26. Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning cs.AI · 2026 · author #7
  27. All Changes May Have Invariant Principles: Improving Ever-Shifting Harmful Meme Detection via Design Concept Reproduction cs.CV · 2026 · author #3
  28. Adversarial Attack on Black-Box Multi-Agent by Adaptive Perturbation cs.MA · 2025 · author #3
  29. SpecQuant: Spectral Decomposition and Adaptive Truncation for Ultra-Low-Bit LLMs Quantization cs.LG · 2025 · author #3
  30. GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs cs.IR · 2025 · author #11
  31. Fall into a Pit, Gain in a Wit: Cognitive-Guided Harmful Meme Detection via Misjudgment Risk Pattern Retrieval cs.LG · 2025 · author #3
  32. Hybrid Architectures for Language Models: Systematic Analysis and Design Insights cs.CL · 2025 · author #7
  33. Multi-needle Localization for Pelvic Seed Implant Brachytherapy based on Tip-handle Detection and Matching cs.CV · 2025 · author #9
  34. MolPIF: A Parameter Interpolation Flow Model for Molecule Generation cs.LG · 2025 · author #2
  35. Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities cs.CL · 2025 · author #2210
  36. EXPEREPAIR: Dual-Memory Enhanced LLM-based Repository-Level Program Repair cs.SE · 2025 · author #2
  37. One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems cs.CR · 2025 · author #4
  38. The Llama 3 Herd of Models cs.AI · 2024 · author #380
  39. Novel MAB phases and insights into their exfoliation into 2D MBenes cond-mat.mtrl-sci · 2019 · author #2
  40. Lane Change Decision-making through Deep Reinforcement Learning with Rule-based Constraints cs.RO · 2019 · author #1
  41. Superion: Grammar-Aware Greybox Fuzzing cs.CR · 2018 · author #1
  42. Ternary Inorganic Electrides with mixed bonding cond-mat.mtrl-sci · 2018 · author #1
  43. Cutting Away the Confusion From Crowdtesting cs.SE · 2018 · author #1
  44. Effective Automated Decision Support for Managing Crowdtesting cs.SE · 2018 · author #1
  45. Sonication-assisted synthesis of semiconducting atomic crystals of germanium monoselenide: An isostructural and isoelectronic analog of black phosphorous cond-mat.mtrl-sci · 2017 · author #5
  46. Gate-modulated conductance of few-layer WSe_2 field-effect transistors in the subgap regime: Schottky barrier transistor and subgap impurity states cond-mat.mes-hall · 2015 · author #1
  47. Detecting Collusive Cliques in Futures Markets Based on Trading Behaviors from Real Data q-fin.TR · 2011 · author #1
  48. Characteristics of Real Futures Trading Networks q-fin.ST · 2010 · author #1

Mentions

  • 2606.07074 #2 · arxiv_oai · confidence 0.70 Junjie Wang
  • 2606.06324 #2 · arxiv_oai · confidence 0.70 Junjie Wang
  • 1505.00807 #1 · backfill · confidence 0.70 Junjie Wang
  • 2606.03220 #3 · arxiv_oai · confidence 0.70 Junjie Wang
  • 2604.15097 #1 · arxiv_oai · confidence 0.70 Junjie Wang
  • 2606.02315 #4 · arxiv_oai · confidence 0.70 Junjie Wang
  • 2606.01844 #2 · arxiv_oai · confidence 0.70 Junjie Wang
  • 2606.01598 #2 · arxiv_oai · confidence 0.70 Junjie Wang
  • 2606.00755 #5 · arxiv_oai · confidence 0.70 Junjie Wang
  • 2605.30789 #8 · arxiv_oai · confidence 0.70 Junjie Wang
  • 2507.13762 #2 · arxiv_oai · confidence 0.70 Junjie Wang
  • 2601.22466 #2 · arxiv_oai · confidence 0.70 Junjie Wang
  • 1110.1522 #1 · backfill · confidence 0.70 Junjie Wang
  • 2509.17931 #9 · arxiv_oai · confidence 0.70 Junjie Wang
  • 2605.19639 #1 · arxiv_oai · confidence 0.70 Junjie Wang
  • 2605.18683 #26 · arxiv_oai · confidence 0.70 Junjie Wang
  • 2605.17583 #5 · arxiv_oai · confidence 0.70 Junjie Wang
  • 1004.4402 #1 · backfill · confidence 0.70 Junjie Wang

Frequent Coauthors