13 papers
Nonadiabatic polaron dynamics from machine-learned hopping trajectories
Daniela Mangano, Luca Leoni, Zhongfei Xu +2
The formation and motion of small polarons are ubiquitous in energy materials and influence photoinduced processes. Polaron transport is governed by thermally activated lattice dyn…
Dr. Free: You Don't Need Difficulty Rewards for Self-Evolving Search Agents
Zhipeng Qian, Zihan Liang, Yufei Ma +10
A central limitation of current data-free self-evolution methods for training search agents is their reliance on difficulty-based proposer rewards. These methods reward a proposer…
Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs
Yunheng Li, Guohong Mu, Hao Li +4
Multimodal large language models (MLLMs) have become a prevailing paradigm for unified video perception. However, post-training on large multi-task datasets remains challenging, as…
RecoReward: Recommender-Guided Multimodal Description Generation for Recommendation
Guohong Mu, Yueyang Liu, Jiangxia Cao +8
Multimodal large language models (MLLMs) can convert multimodal item content into structured descriptions used as semantic features for recommendation. Conventional content-only ge…
Plan Before Search: Search Agents Need Plan
Zhipeng Qian, Zihan Liang, Yufei Ma +7
Training large language models as retrieval-augmented reasoning agents typically combines reinforcement learning with an SFT cold start distilled from a stronger model. However, th…
SLIP-RS: Structured-Attribute Language-Image Pre-Training for Remote Sensing Object Detection
Chenxu Wang, Yuxuan Li, Yunheng Li +3
Existing language-image pre-training for remote sensing object detection is constrained by Monolithic Label Learning, which relies on exhaustively enumerating open-set categories v…
See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding
Boyuan Sun, Bowen Yin, Yuanming Li +2
We present SWIM (See What I Mean), a novel training strategy that aligns vision and language representations to enable fine-grained object understanding solely from textual prompts…
Degradation Frequency Curve: An Explicit Frequency-Quantified Representation for All-in-One Image Restoration
Xinghua Huang, Zhixiong Yang, Chen Wu +6
A fundamental difficulty in all-in-one blind image restoration is that degradation is usually treated as an implicit factor hidden in degraded-to-clean mapping, rather than as an e…
Easy Samples Are All You Need: Self-Evolving LLMs via Data-Efficient Reinforcement Learning
Zhiyin Yu, Bo Zhang, Qibin Hou +3
Previous LLMs-based RL studies typically follow either supervised learning with high annotation costs, or unsupervised paradigms using voting or entropy-based rewards. However, the…
GeoAgent: Learning to Geolocate Everywhere with Reinforced Geographic Characteristics
Modi Jin, Yiming Zhang, Boyuan Sun +3
This paper presents GeoAgent, a model capable of reasoning closely with humans and deriving fine-grained address conclusions. Previous RL-based methods have achieved breakthroughs…
Depth Anything at Any Condition
Boyuan Sun, Modi Jin, Bowen Yin +1
We present Depth Anything at Any Condition (DepthAnything-AC), a foundation monocular depth estimation (MDE) model capable of handling diverse environmental conditions. Previous fo…
LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs
Boyuan Sun, Jiaxing Zhao, Xihan Wei +1
In this paper, we present LLaVA-Scissor, a training-free token compression strategy designed for video multimodal large language models. Previous methods mostly attempt to compress…
LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video Understanding
Boyuan Sun, Jiaxing Zhao, Xiang Chen +2
In this paper, we introduce LLaVA-Octopus, a novel video multimodal large language model. LLaVA-Octopus adaptively weights features from different visual projectors based on user i…