PPaperPicks

Yike Guo

Imperial College London, UK

65 papers at tracked venues · 55 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. ActorMind: Emulating Human Actor Reasoning for Speech Role-Playing
  2. BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook
  3. Benchmarking Fine-Grained Error Detection in Multimodal Reasoning
  4. Bit-by-Bit: Progressive QAT Strategy with Outlier Channel Splitting for Stable Low-Bit LLMs
  5. CareerCraft: Supporting New Graduates on Job Hunting with LLM-Assisted Self-Construction of Career Profile
  6. Glance-or-Gaze: Incentivizing LMMs to Adaptively Focus Search via Reinforcement Learning
  7. Inference-time Scaling for Diffusion-based Audio Super-resolution
  8. InsightEval: An Expert-Curated Benchmark for Assessing Insight Discovery in LLM-Driven Data Agents
  9. Learning While Staying Curious: Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models
  10. Lighthouse: A Self-Reconfiguring Sociotechnical Infrastructure for the Unforeseen Long-Tail of Urban Crisis
  11. Omni-RewardBench: Toward a Comprehensive Evaluation of Generative Reward Models Across Modalities
  12. Outlier Matters: Efficient Long-to-Short Reasoning via Outlier-Guided Model Merging
  13. QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training-Inference Mismatch
  14. Reimagining Legal Fact Verification with GenAI: Toward Effective Human-AI Collaboration
  15. SafeMT: Multi-turn Safety for Multimodal Language Models
  16. Sparse Adapter Fusion for Continual Learning in NLP
  17. Spatiotemporal Graph Learning with Direct Volumetric Information Passing and Feature Enhancement
  18. Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging
  19. VizoMem: A Visual-Textual Memory Framework for Efficient Long-Horizon Reasoning
  20. When Slower Isn't Truer: Inverse Scaling Law of Truthfulness in Multimodal Reasoning
  21. AIRA: Activation-Informed Low-Rank Adaptation for Large Models
  22. Automate Strategy Finding with LLM in Quant Investment
  23. BayesKD: Bayesian Knowledge Distillation for Compact LLMs in Constrained Fine-tuning Scenarios
  24. Benchmarking Multi-National Value Alignment for Large Language Models
  25. Boosting Policy and Process Reward Models with Monte Carlo Tree Search in Open-Domain QA
  26. Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation
  27. Co3Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion
  28. Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model
  29. Conservation-informed Graph Learning for Spatiotemporal Dynamics Prediction
  30. Delta Decompression for MoE-based LLMs Compression
  31. Efficient Fine-Tuning of Large Models Via Nested Low-Rank Adaptation
  32. Empowering World Models with Reflection for Embodied Video Prediction
  33. FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation
  34. Foundation Cures Personalization: Improving Personalized Models' Prompt Consistency via Hidden Foundation Knowledge
  35. Generative RLHF-V: Learning Principles from Multi-modal Human Preference
  36. Graceful Forgetting in Generative Language Models
  37. Importance Weighting Can Help Large Language Models Self-Improve
  38. InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback
  39. LegalReasoner: Step-wised Verification-Correction for Legal Judgment Reasoning
  40. MoE-SVD: Structured Mixture-of-Experts LLMs Compression via Singular Value Decomposition
  41. Outlier-Aware Model Merging for Efficient Multitask Inference
  42. PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference
  43. PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing
  44. STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs
  45. Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback
  46. SafeLawBench: Towards Safe Alignment of Large Language Models
  47. Scenario, Role, and Persona: A Scoping Review of Design Strategies for Socially Intelligent AI Agents
  48. T3D: Advancing 3D Medical Vision-Language Pre-Training by Learning Multi-View Visual Consistency
  49. Task-wrapped Continual Learning in Task-Oriented Dialogue Systems
  50. Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving
  51. VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling
  52. AttnZero: Efficient Attention Discovery for Vision Transformers
  53. Auto-GAS: Automated Proxy Discovery for Training-Free Generative Architecture Search
  54. ChatMusician: Understanding and Generating Music Intrinsically with LLM
  55. DetKDS: Knowledge Distillation Search for Object Detectors
  56. Dirichlet Continual Learning: Tackling Catastrophic Forgetting in NLP
  57. Discovering Sparsity Allocation for Layer-wise Pruning of Large Language Models
  58. Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention
  59. FastSAG: Towards Fast Non-Autoregressive Singing Accompaniment Generation
  60. FlashSpeech: Efficient Zero-Shot Speech Synthesis
  61. Hierarchical Linear Symbolized Tree-Structured Neural Processes
  62. MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training
  63. PyramidCodec: Hierarchical Codec for Long-form Music Generation in Audio Domain
  64. Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training
  65. Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-Speech Gesture Generation