Trending Research
LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control
Instead of following mainstream diffusion-based methods, we explore and extend the potential of the implicit-keypoint-based framework, which effectively balances computational efficiency and controllability.
MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention
With the pattern and sparse indices, we perform efficient sparse attention calculations via our optimized GPU kernels to significantly reduce the latency in the pre-filling stage of long-context LLMs.
RouteLLM: Learning to Route LLMs with Preference Data
lm-sys/routellm
•
•
Large language models (LLMs) exhibit impressive capabilities across a wide range of tasks, yet the choice of which model to use often involves a trade-off between performance and cost.
Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
buoyancy99/diffusion-forcing
•
•
This paper presents Diffusion Forcing, a new training paradigm where a diffusion model is trained to denoise a set of tokens with independent per-token noise levels.
Agentless: Demystifying LLM-based Software Engineering Agents
However, the complexity of these agent-based approaches, together with the limited abilities of current LLMs, raises the following question: Do we really have to employ complex autonomous software agents?
Be-Your-Outpainter: Mastering Video Outpainting through Input-Specific Adaptation
We introduce MOTIA Mastering Video Outpainting Through Input-Specific Adaptation, a diffusion-based pipeline that leverages both the intrinsic data-specific patterns of the source video and the image/video generative prior for effective outpainting.
HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models
In order to thrive in hostile and ever-changing natural environments, mammalian brains evolved to store large amounts of knowledge about the world and continually integrate new information while avoiding catastrophic forgetting.
Occupancy as Set of Points
hustvl/osp
•
•
Owing to the inherent flexibility of the point-based representation, OSP achieves strong performance compared with existing methods and excels in terms of training and inference adaptability.
Self-Play Preference Optimization for Language Model Alignment
uclaml/sppo
•
•
Our method can effectively increase the log-likelihood of the chosen response and decrease that of the rejected response, which cannot be trivially achieved by symmetric pairwise loss such as Direct Preference Optimization (DPO) and Identity Preference Optimization (IPO).
Scaling Synthetic Data Creation with 1,000,000,000 Personas
We propose a novel persona-driven data synthesis methodology that leverages various perspectives within a large language model (LLM) to create diverse synthetic data.
