PPaperPicks

Lei Li

Carnegie Mellon University, School of Computer Science, Language Technologies Institute, Pittsburgh, PA, USA

42 papers at tracked venues · 25 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. CodeEvo: Interaction-Driven Synthesis of Code-centric Data through Hybrid and Iterative Feedback
  2. Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speech
  3. A Practical Examination of AI-Generated Text Detectors for Large Language Models
  4. A Technical Report on "Erasing the Invisible": The 2024 NeurIPS Competition on Stress Testing Image Watermarks
  5. Anticipating Future with Large Language Model for Simultaneous Machine Translation
  6. BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models
  7. BioGraphia: A LLM-Assisted Biological Pathway Graph Annotation Platform
  8. CA*: Addressing Evaluation Pitfalls in Computation-Aware Latency for Simultaneous Speech Translation
  9. DIS-CO: Discovering Copyrighted Content in VLMs Training Data
  10. Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents
  11. Efficiently Identifying Watermarked Segments in Mixed-Source Texts
  12. InfiniSST: Simultaneous Translation of Unbounded Speech with Large Language Model
  13. KS-Lottery: Finding Certified Lottery Tickets for Multilingual Transfer in Large Language Models
  14. LegoMT2: Selective Asynchronous Sharded Data Parallel Training for Massive Neural Machine Translation
  15. PPDiff: Diffusing in Hybrid Sequence-Structure Space for Protein-Protein Complex Design
  16. Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs
  17. Revealing the Barriers of Language Agents in Planning
  18. Scaling LLM Inference Efficiently with Optimized Sample Compute Allocation
  19. Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling
  20. TypedThinker: Diversify Large Language Model Reasoning with Typed Thinking
  21. Weak-to-Strong Jailbreaking on Large Language Models
  22. A Survey on In-context Learning
  23. BPO: Staying Close to the Behavior LLM Creates Better Online LLM Alignment
  24. DE-COP: Detecting Copyrighted Content in Language Models Training Data
  25. Generative Enzyme Design Guided by Functionally Important Sites and Small-Molecule Substrates
  26. Global Human-guided Counterfactual Explanations for Molecular Properties via Reinforcement Learning
  27. Hire a Linguist!: Learning Endangered Languages in LLMs with In-Context Linguistic Descriptions
  28. How Vocabulary Sharing Facilitates Multilingualism in LLaMA?
  29. Invisible Image Watermarks Are Provably Removable Using Generative AI
  30. LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback
  31. LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages
  32. Learning Personalized Alignment for Evaluating Open-ended Text Generation
  33. LumberChunker: Long-Form Narrative Document Segmentation
  34. MindMerger: Efficiently Boosting LLM Reasoning in non-English Languages
  35. Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis
  36. Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement
  37. Provable Robust Watermarking for AI-Generated Text
  38. SnapNTell: Enhancing Entity-Centric Visual Question Answering with Retrieval Augmented Multimodal LLM
  39. SurfPro: Functional Protein Design Based on Continuous Surface
  40. Translation Canvas: An Explainable Interface to Pinpoint and Analyze Translation Systems
  41. Watermarking for Large Language Models
  42. Where It Really Matters: Few-Shot Environmental Conservation Media Monitoring for Low-Resource Languages