Showing 1–20 of 24 results
/ Date/ Name
Feb 6, 2024DistiLLM: Towards Streamlined Distillation for Large Language ModelsMar 10, 2025DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMsMay 24, 2025Flex-Judge: Text-Only Reasoning Unleashes Zero-Shot Multimodal EvaluatorsJun 15, 2022A Gift from Label Smoothing: Robust Training with Adaptive Label Smoothing via Auxiliary Classifier under Label NoiseNov 27, 2023Towards Difficulty-Agnostic Efficient Transfer Learning for Vision-Language ModelsOct 12, 2024SeRA: Self-Reviewing and Alignment of Large Language Models using Implicit Reward MarginsMar 11, 2026Scaling Reasoning Efficiently via Relaxed On-Policy DistillationFeb 3, 2023Revisiting Intermediate Layer Distillation for Compressing Language Models: An Overfitting PerspectiveOct 16, 2023NASH: A Simple Unified Framework of Structured Pruning for Accelerating Encoder-Decoder Language ModelsFeb 10, 2023CUDA: Curriculum of Data Augmentation for Long-Tailed RecognitionJan 27, 2026StableQAT: Stable Quantization-Aware Training at Ultra-Low BitwidthsOct 18, 2022Synergy with Translation Artifacts for Training and Inference in Multilingual TasksSep 11, 2024HESSO: Towards Automatic Efficient and User Friendly Any Neural Network Training and PruningApr 19, 2025Bayesian Principles Improve Prompt Learning In Vision-Language ModelsOct 24, 2023Fine tuning Pre trained Models for Robustness Under Noisy LabelsJan 28, 2026CUA-Skill: Develop Skills for Computer Using AgentFeb 23, 2021FINE Samples for Learning with Noisy LabelsJun 29, 2021Self-Contrastive Learning: Single-viewed Supervised Contrastive Framework using Sub-networkOct 3, 2024Beyond correlation: The Impact of Human Uncertainty in Measuring the Effectiveness of Automatic Evaluation and LLM-as-a-JudgeMay 29, 2025Revisiting Multi-Agent Debate as Test-Time Scaling: A Systematic Study of Conditional Effectiveness