Trending Research
Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control
Diffusion models have demonstrated impressive performance in generating high-quality videos from text prompts or images.
Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks
hhhuang/cag
•
•
With the advent of large language models (LLMs) featuring significantly extended context windows, this paper proposes an alternative paradigm, cache-augmented generation (CAG) that bypasses real-time retrieval.
DeepSeek-V3 Technical Report
We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
WebWalker: Benchmarking LLMs in Web Traversal
Extensive experimental results show that WebWalkerQA is challenging and demonstrates the effectiveness of RAG combined with WebWalker, through the horizontal and vertical integration in real-world scenarios.
A General Framework for Inference-time Scaling and Steering of Diffusion Models
zacharyhorvitz/fk-diffusion-steering
•
•
For steering text-to-image models with a human preference reward, we find that FK steering a 0. 8B parameter model outperforms a 2. 6B parameter fine-tuned model on prompt fidelity, with faster sampling and no training.
Generative AI for Cel-Animation: A Survey
Traditional Celluloid (Cel) Animation production pipeline encompasses multiple essential steps, including storyboarding, layout design, keyframe animation, inbetweening, and colorization, which demand substantial manual effort, technical expertise, and significant time investment.
VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
VITA-MLLM/VITA
•
•
Recent Multimodal Large Language Models (MLLMs) have typically focused on integrating visual and textual modalities, with less emphasis placed on the role of speech in enhancing interaction.
Eliza: A Web3 friendly AI Agent Operating System
AI Agent, powered by large language models (LLMs) as its cognitive core, is an intelligent agentic system capable of autonomously controlling and determining the execution paths under user's instructions.
DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing
Our evaluation on four different unstructured document analysis tasks demonstrates that DocETL finds plans with outputs that are 25 to 80% more accurate than well-engineered baselines, addressing a critical gap in unstructured data analysis.
O1 Replication Journey -- Part 3: Inference-time Scaling for Medical Reasoning
Building upon our previous investigations of O1 replication (Part 1: Journey Learning [Qin et al., 2024] and Part 2: Distillation [Huang et al., 2024]), this work explores the potential of inference-time scaling in large language models (LLMs) for medical reasoning tasks, ranging from diagnostic decision-making to treatment planning.
