pith. sign in

Wenda Li

Identifiers

  • name variant Wenda Li 0.60 · backfill

Papers (37)

  1. Pythagoras-Prover: Advancing Efficient Formal Proving via Augmented Lean Formalisation cs.AI · 2026 · author #6
  2. Specialize Roles, Mix Deployments: Pushing the Cost-Accuracy Frontier of LLM Agent Teams cs.MA · 2026 · author #7
  3. Hierarchical Alignment: Enforcing Hierarchical Instruction-Following in LLMs through Logical Consistency cs.CL · 2026 · author #4
  4. Can I Have Your Order? Monte-Carlo Tree Search for Slot Filling Ordering in Diffusion Language Models cs.AI · 2026 · author #4
  5. Coarse-to-Fine Hierarchical Alignment for UAV-based Human Detection using Diffusion Models cs.CV · 2025 · author #1
  6. PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains cs.CL · 2025 · author #7
  7. Eeyore: Realistic Depression Simulation via Supervised and Preference Optimization cs.CL · 2025 · author #3
  8. Formal Mathematical Reasoning: A New Frontier in AI cs.AI · 2024 · author #4
  9. End-to-End Ontology Learning with Large Language Models cs.LG · 2024 · author #3
  10. Learning a Mini-batch Graph Transformer via Two-stage Interaction Augmentation cs.LG · 2024 · author #1
  11. Repurposing Language Models into Embedding Models: Finding the Compute-Optimal Recipe cs.LG · 2024 · author #4
  12. Proving Theorems Recursively cs.AI · 2024 · author #4
  13. DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data cs.AI · 2024 · author #8
  14. Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization cs.AI · 2024 · author #3
  15. Multilingual Mathematical Autoformalization cs.CL · 2023 · author #2
  16. Message-passing selection: Towards interpretable GNNs for graph classification cs.LG · 2023 · author #1
  17. Evaluating Language Models for Mathematics through Interactions cs.LG · 2023 · author #12
  18. Decomposing the Enigma: Subgoal-based Demonstration Learning for Formal Theorem Proving cs.CL · 2023 · author #2
  19. A large-scale multimodal dataset of human speech recognition eess.SP · 2023 · author #5
  20. Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs cs.AI · 2022 · author #4
  21. Autoformalization with Large Language Models cs.LG · 2022 · author #3
  22. Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers cs.AI · 2022 · author #2
  23. MDPose: Human Skeletal Motion Reconstruction Using WiFi Micro-Doppler Signatures cs.CV · 2022 · author #2
  24. OPERAnet: A Multimodal Activity Recognition Dataset Acquired from Radio Frequency and Vision-based Sensors eess.SP · 2021 · author #2
  25. Neural Style Transfer Enhanced Training Support For Human Activity Recognition eess.SP · 2021 · author #2
  26. FMNet: Latent Feature-wise Mapping Network for Cleaning up Noisy Micro-Doppler Spectrogram eess.SP · 2021 · author #2
  27. Simple Type Theory is not too Simple: Grothendieck's Schemes without Dependent Types math.AG · 2021 · author #3
  28. Unsupervised Doppler Radar-Based Activity Recognition for e-Healthcare cs.LG · 2021 · author #3
  29. SimHumalator: An Open Source WiFi Based Passive Radar Human Simulator For Activity Recognition eess.SP · 2021 · author #2
  30. Learning from Natural Noise to Denoise Micro-Doppler Spectrogram eess.SP · 2021 · author #2
  31. LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning cs.LG · 2021 · author #3
  32. Irrationality and Transcendence Criteria for Infinite Series in Isabelle/HOL cs.LO · 2021 · author #2
  33. IsarStep: a Benchmark for High-level Mathematical Reasoning cs.LO · 2020 · author #1
  34. Counting Polynomial Roots in Isabelle/HOL: A Formal Proof of the Budan-Fourier Theorem cs.LO · 2018 · author #1
  35. Evaluating Winding Numbers and Counting Complex Roots through Cauchy Indices in Isabelle/HOL cs.LO · 2018 · author #1
  36. Exploiting WiFi Channel State Information for Residential Healthcare Informatics eess.SP · 2017 · author #5
  37. Deciding Univariate Polynomial Problems Using Untrusted Certificates in Isabelle/HOL cs.LO · 2015 · author #1

Mentions

  • 2503.00018 #3 · arxiv_oai · confidence 0.70 Wenda Li
  • 2412.16075 #4 · arxiv_oai · confidence 0.70 Wenda Li
  • 2406.04165 #4 · arxiv_oai · confidence 0.70 Wenda Li
  • 2410.23584 #3 · arxiv_oai · confidence 0.70 Wenda Li
  • 2407.09904 #1 · arxiv_oai · confidence 0.70 Wenda Li
  • 2405.14414 #4 · arxiv_oai · confidence 0.70 Wenda Li
  • 2405.14333 #8 · arxiv_oai · confidence 0.70 Wenda Li
  • 2403.18120 #3 · arxiv_oai · confidence 0.70 Wenda Li
  • 2311.03755 #2 · arxiv_oai · confidence 0.70 Wenda Li
  • 2306.01694 #12 · arxiv_oai · confidence 0.70 Wenda Li
  • 2306.02081 #1 · arxiv_oai · confidence 0.70 Wenda Li
  • 2305.16366 #2 · arxiv_oai · confidence 0.70 Wenda Li
  • 2303.08295 #5 · arxiv_oai · confidence 0.70 Wenda Li
  • 2210.12283 #4 · arxiv_oai · confidence 0.70 Wenda Li
  • 2104.09366 #3 · arxiv_oai · confidence 0.70 Wenda Li
  • 2101.05257 #2 · arxiv_oai · confidence 0.70 Wenda Li
  • 2205.12615 #3 · arxiv_oai · confidence 0.70 Wenda Li
  • 2205.10893 #2 · arxiv_oai · confidence 0.70 Wenda Li
  • 2107.07312 #2 · arxiv_oai · confidence 0.70 Wenda Li
  • 2101.06223 #3 · arxiv_oai · confidence 0.70 Wenda Li
  • 2201.04212 #2 · arxiv_oai · confidence 0.70 Wenda Li
  • 2103.10478 #3 · arxiv_oai · confidence 0.70 Wenda Li
  • 2110.04239 #2 · arxiv_oai · confidence 0.70 Wenda Li
  • 2107.12821 #2 · arxiv_oai · confidence 0.70 Wenda Li
  • 2006.09265 #1 · arxiv_oai · confidence 0.70 Wenda Li
  • 2103.01677 #2 · arxiv_oai · confidence 0.70 Wenda Li
  • 2102.06887 #2 · arxiv_oai · confidence 0.70 Wenda Li
  • 1804.03922 #1 · arxiv_oai · confidence 0.70 Wenda Li
  • 1811.11093 #1 · arxiv_oai · confidence 0.70 Wenda Li
  • 1506.08238 #1 · arxiv_oai · confidence 0.70 Wenda Li
  • 1712.03401 #5 · arxiv_oai · confidence 0.70 Wenda Li
  • 2606.20629 #7 · arxiv_oai · confidence 0.70 Wenda Li
  • 2606.12594 #6 · arxiv_oai · confidence 0.70 Wenda Li
  • 2512.13869 #1 · arxiv_oai · confidence 0.70 Wenda Li
  • 1506.08238 #1 · backfill · confidence 0.70 Wenda Li
  • 2602.12586 #4 · arxiv_oai · confidence 0.70 Wenda Li

Frequent Coauthors