Trending Research
OSUM: Advancing Open Speech Understanding Models with Limited Resources in Academia
aslp-lab/osum
•
•
Large Language Models (LLMs) have made significant progress in various downstream tasks, inspiring the development of Speech Understanding Language Models (SULMs) to enable comprehensive speech-based interactions.
Agentic Reasoning: Reasoning LLMs with Tools for the Deep Research
We introduce Agentic Reasoning, a framework that enhances large language model (LLM) reasoning by integrating external tool-using agents.
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
seal-rg/recurrent-pretraining
•
•
We scale a proof-of-concept model to 3. 5 billion parameters and 800 billion tokens.
FlashVideo:Flowing Fidelity to Detail for Efficient High-Resolution Video Generation
foundationvision/flashvideo
•
•
DiT diffusion models have achieved great success in text-to-video generation, leveraging their scalability in model capacity and data scale.
SCoralDet: Efficient real-time underwater soft coral detection with YOLO
RDXiaoLu/SCoralDet-Dataset
•
•
journal 2024
To address these challenges, we propose SCoralDet, a soft coral detection model based on the YOLO architecture.
Ranked #1 on
2D Object Detection
on SCoralDet Dataset
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.
Cut Your Losses in Large-Vocabulary Language Models
We implement a custom kernel that performs the matrix multiplications and the log-sum-exp reduction over the vocabulary in flash memory, making global memory consumption for the cross-entropy computation negligible.
Zep: A Temporal Knowledge Graph Architecture for Agent Memory
We introduce Zep, a novel memory layer service for AI agents that outperforms the current state-of-the-art system, MemGPT, in the Deep Memory Retrieval (DMR) benchmark.
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.
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.
