Trending Research
Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback
pku-alignment/align-anything
•
•
In this work, we make the first attempt to fine-tune all-modality models (i. e. input and output with any modality, also named any-to-any models) using human preference data across all modalities (including text, image, audio, and video), ensuring its behavior aligns with human intentions.
FireRedASR: Open-Source Industrial-Grade Mandarin Speech Recognition Models from Encoder-Decoder to LLM Integration
We present FireRedASR, a family of large-scale automatic speech recognition (ASR) models for Mandarin, designed to meet diverse requirements in superior performance and optimal efficiency across various applications.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
On the Emergence of Thinking in LLMs I: Searching for the Right Intuition
Lastly, we propose a theory as to why RLSP search strategy is more suitable for LLMs inspired by a remarkable result that says CoT provably increases computational power of LLMs, which grows as the number of steps in CoT \cite{li2024chain, merrill2023expresssive}.
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
We present DeepSeek-VL2, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL, through two key major upgrades.
Ranked #1 on
Referring Expression Comprehension
on RefCOCOg-test
LIMO: Less is More for Reasoning
gair-nlp/limo
•
•
While conventional wisdom suggests that sophisticated reasoning tasks demand extensive training data (>100, 000 examples), we demonstrate that complex mathematical reasoning abilities can be effectively elicited with surprisingly few examples.
MedRAX: Medical Reasoning Agent for Chest X-ray
Chest X-rays (CXRs) play an integral role in driving critical decisions in disease management and patient care.
Accelerating Data Processing and Benchmarking of AI Models for Pathology
Advances in foundation modeling have reshaped computational pathology.
Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding
To overcome these challenges, we introduce a specialized cognitive module, temporal working memory (TWM), which aims to enhance the temporal modeling capabilities of MFMs.
Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound
facebookresearch/audiobox-aesthetics
•
•
The quantification of audio aesthetics remains a complex challenge in audio processing, primarily due to its subjective nature, which is influenced by human perception and cultural context.
MatterGen: a generative model for inorganic materials design
We further introduce adapter modules to enable fine-tuning towards any given property constraints with a labeled dataset.
