Data Influence Oriented Tree Search
PulseAugur coverage of Data Influence Oriented Tree Search — every cluster mentioning Data Influence Oriented Tree Search across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New theory explains how diffusion transformers denoise images
Researchers have proposed a new perspective on how diffusion transformers (DiTs) denoise images by viewing them as input-adaptive local denoisers. This framework suggests that context aggregation and patch prediction pl…
-
TamedFlow accelerates diffusion model sampling by bridging compression and adaptive inference
Researchers have developed TamedFlow, a novel method for accelerating diffusion model sampling by combining model compression with adaptive inference techniques. This approach addresses the "Combination Gap," a quality …
-
New research on arXiv introduces advanced time series forecasting techniques · 9 sources tracked
Multiple research papers published on arXiv introduce novel methods for improving time series forecasting. SteerCast enhances decoder-only models by using a database of past data to guide predictions without retraining.…
-
SCOPE framework enhances Diffusion Transformer efficiency for video attention
Researchers have developed SCOPE, a novel training-free sparse attention framework designed to improve the efficiency of Diffusion Transformers (DiTs) in video processing. SCOPE addresses the quadratic cost of self-atte…
-
New BAG policy accelerates Diffusion Transformers with adaptive caching
Researchers have developed BAG (Budget-Aware Gating), a new caching policy designed to accelerate Diffusion Transformers (DiTs). Unlike previous methods that either lacked budget awareness or instance adaptivity, BAG us…
-
Diffusion Transformer study reveals hidden role of text template tokens
Researchers have developed a new interpretability framework for text-to-image diffusion transformers (DiTs) that reveals the crucial role of structural text template tokens. These tokens, often overlooked, act as implic…
-
Diffusion Transformers enhanced for controllable motion transfer via attention head analysis
Researchers have developed a novel framework for controlling motion transfer in Diffusion Transformers (DiTs), a type of model used for advanced video generation. By analyzing DiTs at the attention-head level, they iden…
-
New models improve LLM reasoning evaluation and control over internal states
Researchers have developed a new framework to minimize "collateral damage" in activation steering for large language models (LLMs), which aims to control model behavior without negatively impacting performance on unrela…