↓Skip to main content

🏢 MIT

SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models
·4209 words·20 mins· loading · loading
AI Generated 🤗 Daily Papers Natural Language Processing Large Language Models 🏢 MIT
SelfCite: A self-supervised approach boosts LLM citation accuracy via context ablation. By removing or isolating cited text, SelfCite trains LLMs to generate high-quality citations without manual ann…
Learning Real-World Action-Video Dynamics with Heterogeneous Masked Autoregression
·3466 words·17 mins· loading · loading
AI Generated 🤗 Daily Papers AI Applications Robotics 🏢 MIT
HMA: a novel approach for generating high-quality robotic videos 15x faster, enabling real-time policy evaluation and data augmentation for scaling robot learning.
Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search
·3854 words·19 mins· loading · loading
AI Generated 🤗 Daily Papers Natural Language Processing Large Language Models 🏢 MIT
Satori: A novel 7B LLM achieves state-of-the-art mathematical reasoning via autoregressive search.
A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods
·2572 words·13 mins· loading · loading
AI Generated 🤗 Daily Papers Natural Language Processing Large Language Models 🏢 MIT
Boosting Large Language Model (LLM) inference speed using probabilistic inference via particle-based Monte Carlo methods achieves 4-16x better scaling than deterministic search approaches.
Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning
·5162 words·25 mins· loading · loading
AI Generated 🤗 Daily Papers AI Applications Robotics 🏢 MIT
MoDE makes AI for robot control faster and more efficient.
SketchAgent: Language-Driven Sequential Sketch Generation
·5526 words·26 mins· loading · loading
AI Generated 🤗 Daily Papers Multimodal Learning Human-AI Interaction 🏢 MIT
SketchAgent uses a multimodal LLM to generate dynamic, sequential sketches from textual prompts, enabling collaborative drawing and chat-based editing.
SVDQunat: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
·4041 words·19 mins· loading · loading
AI Generated 🤗 Daily Papers Computer Vision Image Generation 🏢 MIT
SVDQuant boosts 4-bit diffusion models by absorbing outliers via low-rank components, achieving 3.5x memory reduction and 3x speedup on 12B parameter models.