Trending Research
Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting
Document image parsing is challenging due to its complexly intertwined elements such as text paragraphs, figures, formulas, and tables.
Mirage: A Multi-Level Superoptimizer for Tensor Programs
We introduce Mirage, the first multi-level superoptimizer for tensor programs.
LeVo: High-Quality Song Generation with Multi-Preference Alignment
tencent-ailab/songgeneration
•
•
To further enhance musicality and instruction following, we introduce a multi-preference alignment method based on Direct Preference Optimization (DPO).
Do Large Language Models Need a Content Delivery Network?
lmcache/lmcache
•
•
As the use of large language models (LLMs) expands rapidly, so does the range of knowledge needed to supplement various LLM queries.
PixelsDB: Serverless and NL-Aided Data Analytics with Flexible Service Levels and Prices
The queries are then executed by a serverless query engine that offers varying prices for different performance service levels (SLAs).
TradingAgents: Multi-Agents LLM Financial Trading Framework
Significant progress has been made in automated problem-solving using societies of agents powered by large language models (LLMs).
MEIA: Multimodal Embodied Perception and Interaction in Unknown Environments
To overcome this limitation, we introduce the Multimodal Embodied Interactive Agent (MEIA), capable of translating high-level tasks expressed in natural language into a sequence of executable actions.
Visual Causal Scene Refinement for Video Question Answering
hcplab-sysu/causal-vlreasoning
•
•
Our VCSR involves two essential modules: i) the Question-Guided Refiner (QGR) module, which refines consecutive video frames guided by the question semantics to obtain more representative segment features for causal front-door intervention; ii) the Causal Scene Separator (CSS) module, which discovers a collection of visual causal and non-causal scenes based on the visual-linguistic causal relevance and estimates the causal effect of the scene-separating intervention in a contrastive learning manner.
V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
Finally, we show how self-supervised learning can be applied to robotic planning tasks by post-training a latent action-conditioned world model, V-JEPA 2-AC, using less than 62 hours of unlabeled robot videos from the Droid dataset.
Ranked #4 on
Video Question Answering
on TVBench
Stream-Omni: Simultaneous Multimodal Interactions with Large Language-Vision-Speech Model
The emergence of GPT-4o-like large multimodal models (LMMs) has raised the exploration of integrating text, vision, and speech modalities to support more flexible multimodal interaction.
