1 citations · 2 across the 23 of their papers we have counts for
29 papers
SafeAdapt-Poker: Counterfactual Risk Calibration for Budgeted Adaptation under Opponent Shift
Miaobo Hu, Shuhao Hu, Xiaobo Guo +5
Opponent histories can mislead after behavioral shifts. SafeAdapt-Poker formulates budgeted adaptation under opponent shift as a dual-counterfactual sequential-control problem usin…
FACES: Fine-grained Gated Semantic Alignment for Multimodal Emotional Support Conversation
Hang Ren, Peidong Wang, Yichen Gao +4
In recent years, with advances in multimodal interaction technologies and the growing demand for intelligent emotional support, Multimodal Emotional Support Conversation (MESC) has…
Decide, Don't Generate: Competitive Dimensional ABSA with Jev's Typed Decisions
Yiqun Zhang, Peidong Wang, Zihan Wang +1
Aspect-based sentiment analysis (ABSA) has largely turned to text generation. We show that competitive dimensional ABSA does not need it. Using Jev, a frozen model that answers typ…
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
DeepSeek-AI, :, Anyi Xu +585
The widespread adoption of long-horizon agents has made model workloads increasingly input-heavy. Although prior work has substantially reduced the cost of long-context computation…
Self-Evolving Embodied Agents via Skill-Harness Evolution
Peidong Wang, Zhiming Ma, Ying Chang +7
Embodied agents are increasingly built as systems around foundation models, where performance depends not only on model weights but also on the skills, context, action interfaces,…
A Target-Centric Survey of Quantization-Aware Training
Jiamin Song, Mengjie Zhao, Zijing Wang +6
The rapid development of LLMs incurs prohibitive memory footprints and intensive computational demands. Quantization-Aware Training (QAT) techniques have emerged as a promising sol…
HarmTrace: Anchor-Calibrated Decoupled Optimization for Fine-Grained Target Identification in Harmful Memes
Yujia Li, Yiqun Zhang, Zihan Cheng +7
Multimodal harmful meme detection is typically formulated as image--text harmfulness classification. A model may correctly predict harmfulness while misidentifying the attacked tar…
Better Decomposition, Free Aggregation: A Synthesizer-Folding Framework for Multilingual Multi-Hop Question Answering
Yilin Wang, Yuchun Fan, Weidong Bao +5
Multilingual retrieval-augmented generation (mRAG) equips large language models with access to globally distributed external knowledge for complex multilingual question answering.…
Boosting Deepresearch and LongContext Ability with Self-Generated Deepresearch Rollouts Traces
Zihan Wang, Hao Wang, Boyuan Jiang +8
Deepresearch (DR) agents interact with real-world web environments through multi-turn search and visit, causing their contexts to grow rapidly over time. We observe that, even afte…
TRAM: Enhancing Multimodal Reasoning with Trajectory-Derived Auxiliary Memory
Kang Liu, Zijing Wang, Yongkang Liu +5
Multimodal Large Reasoning Models (MLRMs) have achieved strong performance on tasks requiring visual understanding and multi-step inference. However, as reasoning trajectories grow…
SAILRec: Steering LLM Attention to Dual-Side Semantically Aligned Collaborative Embeddings for Recommendation
Xi Wu, Jiale Wang, Zihan Wang +5
Recent LLM-based recommenders enhance language models with collaborative embeddings from user-item interactions, but making such embeddings available does not ensure their proper u…
Covert Influence Between Language Models
Avidan Shah, Jay Chooi, Jinghua Ou +1
As language models increasingly consume one another's outputs, covert influence -- a phenomenon where a sender's payload (the behavioral disposition it is conditioned to propagate)…
ChunkFT: Byte-Streamed Optimization for Memory-Efficient Full Fine-Tuning
Yongkang Liu, Zijing Wang, Mengjie Zhao +7
This work presents \textsc{ChunkFT}, a memory-efficient fine-tuning framework that reformulates full-parameter fine-tuning around a dynamically activated working set. \textsc{Chunk…
SMoA: Spectrum Modulation Adapter for Parameter-Efficient Fine-Tuning
Yongkang Liu, Xing Li, Mengjie Zhao +7
As the number of model parameters increases, parameter-efficient fine-tuning (PEFT) has become the go-to choice for tailoring pre-trained large language models. Low-rank Adaptation…
A Systematic Analysis of the Impact of Persona Steering on LLM Capabilities
Jiaqi Chen, Ming Wang, Tingna Xie +2
Imbuing Large Language Models (LLMs) with specific personas is prevalent for tailoring interaction styles, yet the impact on underlying cognitive capabilities remains unexplored. W…
How Many Visual Tokens Do Multimodal Language Models Need? Scaling Visual Token Pruning with F^3A
YiJie Huang, Yiqun Zhang, Zhuoyue Jia +7
Vision-language models improve perception by feeding increasingly long visual token sequences into language backbones, but the resulting inference cost raises a basic scaling quest…
GRASP: Grounded CoT Reasoning with Dual-Stage Optimization for Multimodal Sarcasm Target Identification
Faxian Wan, Xiaocui Yang, Yifan Cao +3
Moving beyond the traditional binary classification paradigm of Multimodal Sarcasm Detection, Multimodal Sarcasm Target Identification (MSTI) presents a more formidable challenge,…
NEAT: Neuron-Based Early Exit for Large Reasoning Models
Kang Liu, Yongkang Liu, Xiaocui Yang +5
Large Reasoning Models (LRMs) often suffer from \emph{overthinking}, a phenomenon in which redundant reasoning steps are generated after a correct solution has already been reached…
Defending Large Language Models Against Jailbreak Attacks via In-Decoding Safety-Awareness Probing
Yinzhi Zhao, Ming Wang, Shi Feng +3
Large language models (LLMs) have achieved impressive performance across natural language tasks and are increasingly deployed in real-world applications. Despite extensive safety a…
PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs
Zijing Wang, Yongkang Liu, Mingyang Wang +8
Multimodal Large Language Models (MLLMs) rely on strong linguistic reasoning inherited from their base language models. However, multimodal instruction fine-tuning paradoxically de…
High-Rank Structured Modulation for Parameter-Efficient Fine-Tuning
Yongkang Liu, Xing Li, Mengjie Zhao +7
As the number of model parameters increases, parameter-efficient fine-tuning (PEFT) has become the go-to choice for tailoring pre-trained large language models. Low-rank Adaptation…
SAD: A Large-Scale Strategic Argumentative Dialogue Dataset
Yongkang Liu, Jiayang Yu, Mingyang Wang +6
Argumentation generation has attracted substantial research interest due to its central role in human reasoning and decision-making. However, most existing argumentative corpora fo…
CIRAG: Construction-Integration Retrieval and Adaptive Generation for Multi-hop Question Answering
Zili Wei, Xiaocui Yang, Yilin Wang +5
Triple-based Iterative Retrieval-Augmented Generation (iRAG) mitigates document-level noise for multi-hop question answering. However, existing methods still face limitations: (i)…
SAFE-QAQ: End-to-End Slow-Thinking Audio-Text Fraud Detection via Reinforcement Learning
Peidong Wang, Zhiming Ma, Xin Dai +8
Existing fraud detection methods predominantly rely on transcribed text, suffering from ASR errors and missing crucial acoustic cues like vocal tone and environmental context. This…