User contributions for W269wang

4 April 2025

• 00:3000:30, 4 April 2025 diff hist +1,683‎ stat946W25 ‎ →‎Masked-Diffusion LM: Faster and Smarter
• 00:0500:05, 4 April 2025 diff hist +1,717‎ stat946W25 ‎ →‎Graph-RAG for Document Set Summarization

27 March 2025

• 14:4814:48, 27 March 2025 diff hist +1,924‎ stat946W25 ‎ →‎Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers

20 March 2025

• 03:4403:44, 20 March 2025 diff hist +973‎ stat946W25 ‎ →‎Compact Language Models via Pruning and Knowledge Distillation
• 03:4203:42, 20 March 2025 diff hist +756‎ stat946W25 ‎ →‎Limitation and Future Work
• 03:2903:29, 20 March 2025 diff hist +68‎ stat946W25 ‎ →‎Topic 5: KD / Pruning / Sharing

14 March 2025

• 19:2719:27, 14 March 2025 diff hist +309‎ stat946W25 ‎ →‎Advantages of SSMs

13 March 2025

• 00:2500:25, 13 March 2025 diff hist −993‎ stat946W25 ‎ →‎Simple linear attention language models balance the recall-throughput tradeoff
• 00:2500:25, 13 March 2025 diff hist −1,326‎ stat946W25 ‎ →‎Retentive Network (RetNet): A Successor to Transformer for Large Language Models