Trending Research
FastVLM: Efficient Vision Encoding for Vision Language Models
apple/ml-fastvlm
•
•
At different operational resolutions, the vision encoder of a VLM can be optimized along two axes: reducing encoding latency and minimizing the number of visual tokens passed to the LLM, thereby lowering overall latency.
Continuous Thought Machines
SakanaAI/continuous-thought-machines
•
•
The CTM has two core innovations: (1) neuron-level temporal processing, where each neuron uses unique weight parameters to process a history of incoming signals; and (2) neural synchronization employed as a latent representation.
BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset
Building on our innovative model design, training recipe, and datasets, we develop BLIP3-o, a suite of state-of-the-art unified multimodal models.
Generating Physically Stable and Buildable LEGO Designs from Text
Our experiments show that LegoGPT produces stable, diverse, and aesthetically pleasing LEGO designs that align closely with the input text prompts.
Flow-GRPO: Training Flow Matching Models via Online RL
We propose Flow-GRPO, the first method integrating online reinforcement learning (RL) into flow matching models.
Ranked #1 on
Text-to-Image Generation
on GenEval
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
LeapLabTHU/Absolute-Zero-Reasoner
•
•
Reinforcement learning with verifiable rewards (RLVR) has shown promise in enhancing the reasoning capabilities of large language models by learning directly from outcome-based rewards.
HealthBench: Evaluating Large Language Models Towards Improved Human Health
We present HealthBench, an open-source benchmark measuring the performance and safety of large language models in healthcare.
Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models
Large Multimodal Reasoning Models (LMRMs) have emerged as a promising paradigm, integrating modalities such as text, images, audio, and video to support complex reasoning capabilities and aiming to achieve comprehensive perception, precise understanding, and deep reasoning.
UniVLA: Learning to Act Anywhere with Task-centric Latent Actions
Learned from internet-scale videos, the generalist policy can be deployed to various robots through efficient latent action decoding.
VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model
Specifically, we introduce a lightweight Multiple Cross-modal Token Prediction (MCTP) module that efficiently generates multiple audio tokens within a single model forward pass, which not only accelerates the inference but also significantly reduces the latency for generating the first audio in streaming scenarios.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+7
