Trending Research
F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching
SWivid/F5-TTS
•
•
This sampling strategy for flow step can be easily applied to existing flow matching based models without retraining.
LightRAG: Simple and Fast Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) systems enhance large language models (LLMs) by integrating external knowledge sources, enabling more accurate and contextually relevant responses tailored to user needs.
Diffusion for World Modeling: Visual Details Matter in Atari
Motivated by this paradigm shift, we introduce DIAMOND (DIffusion As a Model Of eNvironment Dreams), a reinforcement learning agent trained in a diffusion world model.
Pyramidal Flow Matching for Efficient Video Generative Modeling
Video generation requires modeling a vast spatiotemporal space, which demands significant computational resources and data usage.
DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
Based on this insight, we introduce DuoAttention, a framework that only applies a full KV cache to retrieval heads while using a light-weight, constant-length KV cache for streaming heads, which reduces both LLM's decoding and pre-filling memory and latency without compromising its long-context abilities.
Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
sihyun-yu/REPA
•
•
Recent studies have shown that the denoising process in (generative) diffusion models can induce meaningful (discriminative) representations inside the model, though the quality of these representations still lags behind those learned through recent self-supervised learning methods.
Ranked #1 on
Image Generation
on ImageNet 256x256
HART: Efficient Visual Generation with Hybrid Autoregressive Transformer
mit-han-lab/hart
•
•
To address these challenges, we present the hybrid tokenizer, which decomposes the continuous latents from the autoencoder into two components: discrete tokens representing the big picture and continuous tokens representing the residual components that cannot be represented by the discrete tokens.
Baichuan-Omni Technical Report
The salient multimodal capabilities and interactive experience of GPT-4o highlight its critical role in practical applications, yet it lacks a high-performing open-source counterpart.
LoLCATs: On Low-Rank Linearizing of Large Language Models
When compared with prior approaches under the same compute budgets, LoLCATs significantly improves linearizing quality, closing the gap between linearized and original Llama 3. 1 70B and 405B LLMs by 77. 8% and 78. 1% on 5-shot MMLU.
Generalizable and Animatable Gaussian Head Avatar
xg-chu/gagavatar
•
•
In this paper, we propose Generalizable and Animatable Gaussian head Avatar (GAGAvatar) for one-shot animatable head avatar reconstruction.
