Summary of Token-budget-aware Llm Reasoning, by Tingxu Han et al.
Token-Budget-Aware LLM Reasoningby Tingxu Han, Zhenting Wang, Chunrong Fang, Shiyu Zhao, Shiqing Ma, Zhenyu ChenFirst…
Summary of Next Token Prediction Towards Multimodal Intelligence: a Comprehensive Survey, by Liang Chen et al.
Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Surveyby Liang Chen, Zekun Wang, Shuhuai Ren,…
Summary of Rdpm: Solve Diffusion Probabilistic Models Via Recurrent Token Prediction, by Xiaoping Wu and Jie Hu and Xiaoming Wei
RDPM: Solve Diffusion Probabilistic Models via Recurrent Token Predictionby Xiaoping Wu, Jie Hu, Xiaoming WeiFirst…
Summary of Token Statistics Transformer: Linear-time Attention Via Variational Rate Reduction, by Ziyang Wu et al.
Token Statistics Transformer: Linear-Time Attention via Variational Rate Reductionby Ziyang Wu, Tianjiao Ding, Yifu Lu,…
Summary of Fast Gradient Computation For Rope Attention in Almost Linear Time, by Yifang Chen et al.
Fast Gradient Computation for RoPE Attention in Almost Linear Timeby Yifang Chen, Jiayan Huo, Xiaoyu…
Summary of Distilled Decoding 1: One-step Sampling Of Image Auto-regressive Models with Flow Matching, by Enshu Liu et al.
Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matchingby Enshu Liu, Xuefei…
Summary of Enhancing Item Tokenization For Generative Recommendation Through Self-improvement, by Runjin Chen et al.
Enhancing Item Tokenization for Generative Recommendation through Self-Improvementby Runjin Chen, Mingxuan Ju, Ngoc Bui, Dimosthenis…
Summary of Layer- and Timestep-adaptive Differentiable Token Compression Ratios For Efficient Diffusion Transformers, by Haoran You et al.
Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformersby Haoran You, Connelly Barnes,…
Summary of When Worse Is Better: Navigating the Compression-generation Tradeoff in Visual Tokenization, by Vivek Ramanujan et al.
When Worse is Better: Navigating the compression-generation tradeoff in visual tokenizationby Vivek Ramanujan, Kushal Tirumala,…
Summary of Hashevict: a Pre-attention Kv Cache Eviction Strategy Using Locality-sensitive Hashing, by Minghui Liu et al.
HashEvict: A Pre-Attention KV Cache Eviction Strategy using Locality-Sensitive Hashingby Minghui Liu, Tahseen Rabbani, Tony…