activity
20242026
collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

OTCache: Optimal Transport for Geometry-Aware Caching in Diffusion Models

Huanlin Gao, Fang Zhao, Qiang Hui +8

We propose OTCache, a training-free framework for accelerating diffusion sampling via caching schedule prediction. Existing graph-based caching methods reduce redundant computation…

cs.LG2026

Chain-of-Trajectories: Unlocking the Intrinsic Generative Optimality of Diffusion Models via Graph-Theoretic Planning

Ping Chen, Xiang Liu, Xingpeng Zhang +7

Diffusion models operate in a reflexive System 1 mode, constrained by a fixed, content-agnostic sampling schedule. This rigidity arises from the curse of state dimensionality, wher…

cs.LG2026

MeanCache: From Instantaneous to Average Velocity for Accelerating Flow Matching Inference

Huanlin Gao, Ping Chen, Fuyuan Shi +11

We present MeanCache, a training-free caching framework for efficient Flow Matching inference. Existing caching methods reduce redundant computation but typically rely on instantan…

cs.LG2026

DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models

Yi Shen, Jian Zhang, Jieyun Huang +7

Recent advancements in slow thinking reasoning models have shown exceptional performance in complex reasoning tasks. However, these models often exhibit overthinking (generating re…

cs.LG2025

Quantitative Analysis of Performance Drop in DeepSeek Model Quantization

Enbo Zhao, Yi Shen, Shuming Shi +7

Recently, there is a high demand for deploying DeepSeek-R1 and V3 locally, possibly because the official service often suffers from being busy and some organizations have data priv…