Showing 1–17 of 17 results
/ Date/ Name
Nov 3, 2023Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMsJun 25, 2022PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight ImportanceOct 19, 2023Efficient Long-Range Transformers: You Need to Attend More, but Not Necessarily at Every LayerSep 16, 2024Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention SteeringOct 24, 2025Self-Rewarding PPO: Aligning Large Language Models with Demonstrations OnlyMar 18, 2023AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-TuningMar 1, 2021A Biased Graph Neural Network Sampler with Near-Optimal RegretJun 21, 2024Robust Reinforcement Learning from Corrupted Human FeedbackOct 23, 2025Ask a Strong LLM Judge when Your Reward Model is UncertainSep 29, 2018AdaShift: Decorrelation and Convergence of Adaptive Learning Rate MethodsMar 8, 2024GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLMOct 16, 2023Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable AlgorithmsApr 15, 2022MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided AdaptationMay 26, 2025Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMsOct 4, 2022Less is More: Task-aware Layer-wise Distillation for Language Model CompressionJun 20, 2023LoSparse: Structured Compression of Large Language Models based on Low-Rank and Sparse ApproximationMay 22, 2025Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models