[๋ ผ๋ฌธ๋ฆฌ๋ทฐ] jina-reranker-v3: Last but Not Late Interaction for Document Reranking
์ด [arXiv]์ ๊ฒ์ํ โjina-reranker-v3: Last but Not Late Interaction for Document Rerankingโ ๋ ผ๋ฌธ์ ๋ํ ์์ธํ ๋ฆฌ๋ทฐ์ ๋๋ค.
Recent Posts
[๋ ผ๋ฌธ๋ฆฌ๋ทฐ] dParallel: Learnable Parallel Decoding for dLLMs
์ด [arXiv]์ ๊ฒ์ํ โdParallel: Learnable Parallel Decoding for dLLMsโ ๋ ผ๋ฌธ์ ๋ํ ์์ธํ ๋ฆฌ๋ทฐ์ ๋๋ค.
[๋ ผ๋ฌธ๋ฆฌ๋ทฐ] d^2Cache: Accelerating Diffusion-Based LLMs via Dual Adaptive Caching
Jiarui Wang์ด [arXiv]์ ๊ฒ์ํ โd^2Cache: Accelerating Diffusion-Based LLMs via Dual Adaptive Cachingโ ๋ ผ๋ฌธ์ ๋ํ ์์ธํ ๋ฆฌ๋ทฐ์ ๋๋ค.
[๋ ผ๋ฌธ๋ฆฌ๋ทฐ] Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning
Yue Min์ด [arXiv]์ ๊ฒ์ํ โWinning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuningโ ๋ ผ๋ฌธ์ ๋ํ ์์ธํ ๋ฆฌ๋ทฐ์ ๋๋ค.
[๋ ผ๋ฌธ๋ฆฌ๋ทฐ] Whoโs Your Judge? On the Detectability of LLM-Generated Judgments
์ด [arXiv]์ ๊ฒ์ํ โWhoโs Your Judge? On the Detectability of LLM-Generated Judgmentsโ ๋ ผ๋ฌธ์ ๋ํ ์์ธํ ๋ฆฌ๋ทฐ์ ๋๋ค.