Find a paper
20 results for “distillation”
- Standing on the Shoulders of Giants: Stabilized Knowledge Distillation for Cross--Language Code Clone Detection2605.02860cs.AI
- AsymK-Talker: Real-Time and Long-Horizon Talking Head Generation via Asymmetric Kernel Distillation2605.02948cs.LG
- Multilingual Safety Alignment via Self-Distillation2605.02971cs.LG
- Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe2605.03677cs.LG
- Real Image Denoising with Knowledge Distillation for High-Performance Mobile NPUs2605.03680cs.CV
- SymTorch: Symbolic Distillation of Neural Networks2602.21307cs.LG
- Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency2510.08431cs.CV
- Cross-Tokenizer Likelihood Scoring Algorithms for Language Model Distillation2512.14954cs.CL
- UniComp: A Unified Evaluation of Large Language Model Compression via Pruning, Quantization and Distillation2602.09130cs.LG
- Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization2605.05040cs.LG
- Knowledge Distillation Must Account for What It Loses2604.25110cs.LG
- Continual Distillation of Teachers from Different Domains2605.04059cs.LG
- EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation2605.04062cs.LG
- Validity-Calibrated Reasoning Distillation2605.04078cs.LG
- Learn where to Click from Yourself: On-Policy Self-Distillation for GUI Grounding2605.00642cs.AI
- Budgeted LoRA: Distillation as Structured Compute Allocation for Efficient Inference2605.04341cs.LG
- S^2tory: Story Spine Distillation for Movie Script Summarization2605.03244cs.CL
- Power Distribution Bridges Sampling, Self-Reward RL, and Self-Distillation2605.04542cs.LG
- KaVa: Latent Reasoning via Compressed KV-Cache Distillation2510.02312cs.LG
- Don't Ignore the Tail: Decoupling top-K Probabilities for Efficient Language Model Distillation2602.20816cs.CL