7 citations · 32 across the 52 of their papers we have counts for
16 papers · 1 filter
A Preliminary Study on the Promises and Challenges of Native Top- Sparse Attention
Di Xiu, Hongyin Tang, Bolin Rong +4
Large Language Models (LLMs) are increasingly prevalent in the field of long-context modeling, however, their inference computational costs have become a critical bottleneck hinder…
Optimizing Native Sparse Attention with Latent Attention and Local Global Alternating Strategies
Yuxuan Hu, Jianchao Tan, Jiaqi Zhang +7
In this work, we conduct a systematic analysis of Native Sparse Attention (NSA) and propose targeted improvements that enhance long-context modeling. A key insight is that alternat…
CHIPS: Efficient CLIP Adaptation via Curvature-aware Hybrid Influence-based Data Selection
Xinlin Zhuang, Yichen Li, Xiwei Liu +11
Adapting CLIP to vertical domains is typically approached by novel fine-tuning strategies or by continual pre-training (CPT) on large domain-specific datasets. Yet, data itself rem…
World Simulation with Video Foundation Models for Physical AI
NVIDIA, :, Arslan Ali +87
We introduce [Cosmos-Predict2.5], the latest generation of the Cosmos World Foundation Models for Physical AI. Built on a flow-based architecture, [Cosmos-Predict2.5] unifies Text2…
ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation
Jay Zhangjie Wu, Xuanchi Ren, Tianchang Shen +11
Recent advances in large generative models have greatly enhanced both image editing and in-context image generation, yet a critical gap remains in ensuring physical consistency, wh…
LongCat-Flash Technical Report
Meituan LongCat Team, Bayan, Bei Li +179
We introduce LongCat-Flash, a 560-billion-parameter Mixture-of-Experts (MoE) language model designed for both computational efficiency and advanced agentic capabilities. Stemming f…
Mitigating Hallucinations in Large Vision-Language Models by Self-Injecting Hallucinations
Yifan Lu, Ziqi Zhang, Chunfeng Yuan +5
Large Vision-Language Models (LVLMs) suffer from serious hallucination problems, where the model-generated responses are inconsistent with the visual inputs. Existing hallucination…
Introducing LongCat-Flash-Thinking: A Technical Report
Meituan LongCat Team, Anchun Gui, Bei Li +122
We present LongCat-Flash-Thinking, an efficient 560-billion-parameter open-source Mixture-of-Experts (MoE) reasoning model. Its advanced capabilities are cultivated through a metic…
Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models
Yi Liao, Yu Gu, Yuan Sui +5
Large language models (LLMs) excel at complex reasoning tasks such as mathematics and coding, yet they frequently struggle with simple interactive tasks that young children perform…
Step-Audio 2 Technical Report
Boyong Wu, Chao Yan, Chen Hu +106
This paper presents Step-Audio 2, an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation. By integrating a latent…
StreamAgent: Towards Anticipatory Agents for Streaming Video Understanding
Haolin Yang, Feilong Tang, Lingxiao Zhao +10
Real-time streaming video understanding in domains such as autonomous driving and intelligent surveillance poses challenges beyond conventional offline video processing, requiring…
Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models
Xuanchi Ren, Yifan Lu, Tianshi Cao +13
Collecting and annotating real-world data for safety-critical physical AI systems, such as Autonomous Vehicle (AV), is time-consuming and costly. It is especially challenging to ca…
Adaptive Detoxification: Safeguarding General Capabilities of LLMs through Toxicity-Aware Knowledge Editing
Yifan Lu, Jing Li, Yigeng Zhou +7
Large language models (LLMs) exhibit impressive language capabilities but remain vulnerable to malicious prompts and jailbreaking attacks. Existing knowledge editing methods for LL…
Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control
NVIDIA, :, Hassan Abu Alhaija +38
We introduce Cosmos-Transfer, a conditional world generation model that can generate world simulations based on multiple spatial control inputs of various modalities such as segmen…
GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control
Xuanchi Ren, Tianchang Shen, Jiahui Huang +7
We present GEN3C, a generative video model with precise Camera Control and temporal 3D Consistency. Prior video models already generate realistic videos, but they tend to leverage…
RoCo-Sim: Enhancing Roadside Collaborative Perception through Foreground Simulation
Yuwen Du, Anning Hu, Zichen Chao +6
Roadside Collaborative Perception refers to a system where multiple roadside units collaborate to pool their perceptual data, assisting vehicles in enhancing their environmental aw…