pith. sign in

James Zou

Identifiers

  • name variant James Zou 0.60 · backfill

Papers (81)

  1. Benchmarking AI Agents for Addressing Scientific Challenges Across Scales cs.AI · 2026 · author #31
  2. Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories cs.CV · 2026 · author #6
  3. Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveries cs.CL · 2026 · author #4
  4. On the Relationship Between Activation Outliers and Feature Death in Sparse Autoencoders cs.LG · 2026 · author #3
  5. WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction cs.CV · 2026 · author #13
  6. ReasonOps: Operator Segmentation for LLM Reasoning Traces cs.AI · 2026 · author #3
  7. Automated Benchmark Auditing for AI Agents and Large Language Models cs.CL · 2026 · author #7
  8. Knowledge Graph Modulated Deep Learning for Limited-Sample Clinical Data Analysis cs.LG · 2026 · author #3
  9. Evaluating Commercial AI Chatbots as News Intermediaries cs.CL · 2026 · author #8
  10. Forecasting Scientific Progress with Artificial Intelligence cs.AI · 2026 · author #9
  11. AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration cs.AI · 2026 · author #32
  12. Voice "Cloning" is Style Transfer cs.SD · 2026 · author #6
  13. Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders cs.LG · 2026 · author #12
  14. TERMS-Bench: Diagnosing LLM Negotiation Agents Beyond Deal Rate cs.GT · 2026 · author #8
  15. Unlocking LLM Creativity in Science through Analogical Reasoning cs.AI · 2026 · author #3
  16. A Versatile AI Agent for Rare Disease Diagnosis and Risk Gene Prioritization cs.AI · 2026 · author #12
  17. Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction cs.IR · 2026 · author #14
  18. Recursive Multi-Agent Systems cs.AI · 2026 · author #12
  19. Evaluation-driven Scaling for Scientific Discovery cs.LG · 2026 · author #24
  20. Graph-of-Agents: A Graph-based Framework for Multi-Agent LLM Collaboration cs.AI · 2026 · author #6
  21. Introspective Diffusion Language Models cs.AI · 2026 · author #13
  22. Squeeze Evolve: Unified Multi-Model Orchestration for Verifier-Free Evolution cs.AI · 2026 · author #18
  23. Combee: Scaling Prompt Learning for Self-Improving Language Model Agents cs.AI · 2026 · author #11
  24. The Price Reversal Phenomenon: When Cheaper Reasoning Models Cost More cs.CL · 2026 · author #6
  25. Test-Time Optimization of Physical Query Plans with LLMs cs.DB · 2026 · author #6
  26. Multi-Agent Teams Hold Experts Back cs.MA · 2026 · author #7
  27. Sparse Reward Subsystem in Large Language Models cs.CL · 2026 · author #3
  28. Textual Equilibrium Propagation for Deep Compound AI Systems cs.LG · 2026 · author #3
  29. Learning to Discover at Test Time cs.LG · 2026 · author #9
  30. Can Small Training Runs Reliably Guide Data Curation? Rethinking Proxy-Model Practice cs.LG · 2025 · author #4
  31. Latent Collaboration in Multi-Agent Systems cs.CL · 2025 · author #11
  32. Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models cs.LG · 2025 · author #12
  33. Impatient Users Confuse AI Agents: High-fidelity Simulations of Human Traits for Testing Agents cs.AI · 2025 · author #5
  34. ACT: Agentic Classification Tree cs.LG · 2025 · author #5
  35. Advancing AI Research Assistants with Expert-Involved Learning cs.AI · 2025 · author #29
  36. OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning cs.LG · 2025 · author #6
  37. D-Flow: Multi-modality Flow Matching for D-peptide Design cs.CE · 2024 · author #6
  38. TextGrad: Automatic "Differentiation" via Text cs.CL · 2024 · author #7
  39. Mixture-of-Agents Enhances Large Language Model Capabilities cs.CL · 2024 · author #5
  40. TrustLLM: Trustworthiness in Large Language Models cs.CL · 2024 · author #32
  41. FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance cs.LG · 2023 · author #3
  42. Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models cs.CL · 2022 · author #176
  43. Gradio: Hassle-Free Sharing and Testing of ML Models in the Wild cs.LG · 2019 · author #6
  44. Discovering Conditionally Salient Features with Statistical Guarantees stat.ML · 2019 · author #2
  45. A Knowledge Graph-based Approach for Exploring the U.S. Opioid Epidemic cs.CY · 2019 · author #6
  46. Data Shapley: Equitable Valuation of Data for Machine Learning stat.ML · 2019 · author #2
  47. Analyzing Polarization in Social Media: Method and Application to Tweets on 21 Mass Shootings cs.CL · 2019 · author #4
  48. Contrastive Variational Autoencoder Enhances Salient Features cs.LG · 2019 · author #2
  49. Adaptive Monte Carlo Multiple Testing via Multi-Armed Bandits stat.ME · 2019 · author #2
  50. Concrete Autoencoders for Differentiable Feature Selection and Reconstruction cs.LG · 2019 · author #3
  51. Large-scale Generative Modeling to Improve Automated Veterinary Disease Coding cs.CL · 2018 · author #3
  52. Minimizing Close-k Aggregate Loss Improves Classification cs.LG · 2018 · author #2
  53. Contrastive Multivariate Singular Spectrum Analysis stat.ML · 2018 · author #3
  54. Improving the Stability of the Knockoff Procedure: Multiple Simultaneous Knockoffs and Entropy Maximization stat.ML · 2018 · author #2
  55. Autowarp: Learning a Warping Distance from Unlabeled Time Series Using Sequence Autoencoders cs.LG · 2018 · author #2
  56. Knockoffs for the mass: new feature importance statistics with false discovery guarantees stat.ML · 2018 · author #3
  57. DeepTag: inferring all-cause diagnoses from clinical notes in under-resourced medical domain cs.CL · 2018 · author #7
  58. Multiaccuracy: Black-Box Post-Processing for Fairness in Classification cs.LG · 2018 · author #3
  59. Feedback GAN (FBGAN) for DNA: a Novel Feedback-Loop Architecture for Optimizing Protein Functions q-bio.GN · 2018 · author #2
  60. Stochastic EM for Shuffled Linear Regression stat.ML · 2018 · author #2
  61. CoVeR: Learning Covariate-Specific Vector Representations with Tensor Decompositions cs.CL · 2018 · author #3
  62. Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes cs.CL · 2017 · author #4
  63. NeuralFDR: Learning Discovery Thresholds from Hypothesis Features stat.ME · 2017 · author #3
  64. Interpretation of Neural Networks is Fragile stat.ML · 2017 · author #3
  65. The Effects of Memory Replay in Reinforcement Learning cs.AI · 2017 · author #2
  66. Contrastive Principal Component Analysis stat.ML · 2017 · author #4
  67. Why Adaptively Collected Data Have Negative Bias and How to Correct for It stat.ML · 2017 · author #4
  68. Estimating the unseen from multiple populations cs.LG · 2017 · author #3
  69. Beyond Bilingual: Multi-sense Word Embeddings using Multilingual Context cs.CL · 2017 · author #5
  70. Linear Regression with Shuffled Labels stat.ML · 2017 · author #3
  71. Signal to noise in matching markets cs.GT · 2016 · author #2
  72. Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings cs.CL · 2016 · author #3
  73. Contingent Payment Mechanisms for Resource Utilization cs.GT · 2016 · author #4
  74. Quantifying and Reducing Stereotypes in Word Embeddings cs.CL · 2016 · author #3
  75. Clustering with a Reject Option: Interactive Clustering as Bayesian Prior Elicitation stat.ML · 2016 · author #2
  76. Quantifying the accuracy of approximate diffusions and Markov chains math.ST · 2016 · author #2
  77. Clustering with a Reject Option: Interactive Clustering as Bayesian Prior Elicitation stat.ML · 2016 · author #2
  78. Rich Component Analysis cs.LG · 2015 · author #2
  79. Incentive-Compatible Experimental Design stat.ME · 2015 · author #4
  80. Intersecting Faces: Non-negative Matrix Factorization With New Guarantees cs.LG · 2015 · author #2
  81. Mechanism Design for Time Critical and Cost Critical Task Execution via Crowdsourcing cs.GT · 2012 · author #5

Mentions

  • 2606.12736 #31 · arxiv_oai · confidence 0.70 James Zou
  • 2606.11176 #6 · arxiv_oai · confidence 0.70 James Zou
  • 2606.10402 #4 · arxiv_oai · confidence 0.70 James Zou
  • 2510.04491 #5 · arxiv_oai · confidence 0.70 James Zou
  • 1507.03867 #2 · backfill · confidence 0.70 James Zou
  • 1507.03063 #4 · backfill · confidence 0.70 James Zou
  • 1507.02189 #2 · backfill · confidence 0.70 James Zou
  • 2602.10387 #6 · arxiv_oai · confidence 0.70 James Zou
  • 2511.20639 #11 · arxiv_oai · confidence 0.70 James Zou
  • 2605.31518 #3 · arxiv_oai · confidence 0.70 James Zou
  • 2602.01011 #7 · arxiv_oai · confidence 0.70 James Zou
  • 2605.29341 #13 · arxiv_oai · confidence 0.70 James Zou
  • 2605.29192 #3 · arxiv_oai · confidence 0.70 James Zou
  • 2603.23971 #6 · arxiv_oai · confidence 0.70 James Zou
  • 2605.26079 #7 · arxiv_oai · confidence 0.70 James Zou
  • 2605.24162 #3 · arxiv_oai · confidence 0.70 James Zou
  • 1208.1676 #5 · backfill · confidence 0.70 James Zou
  • 2605.22785 #8 · arxiv_oai · confidence 0.70 James Zou
  • 2605.22681 #9 · arxiv_oai · confidence 0.70 James Zou
  • 2605.20025 #32 · arxiv_oai · confidence 0.70 James Zou
  • 2605.16578 #6 · arxiv_oai · confidence 0.70 James Zou
  • 2605.13930 #12 · arxiv_oai · confidence 0.70 James Zou
  • 2401.05561 #32 · arxiv_oai · confidence 0.70 James Zou
  • 2406.04692 #5 · arxiv_oai · confidence 0.70 James Zou
  • 2601.16175 #9 · arxiv_oai · confidence 0.70 James Zou

Frequent Coauthors