45 citations · 134 across the 47 of their papers we have counts for
49 papers
EchoRL: Reinforcement Learning via Rollout Echoing
Jinhe Bi, Aniri, Minglai Yang +9
Reinforcement Learning with Verifiable Rewards is an effective route for post-training to strengthen the reasoning capability of large language models. However, as training proceed…
Routing-Free Mixture-of-Experts
Yilun Liu, Jinru Han, Sikuan Yan +2
Standard Mixture-of-Experts (MoE) models rely on centralized routing mechanisms that introduce rigid inductive biases. We propose Routing-Free MoE which eliminates any hard-coded c…
Bayes or Heisenberg: Who(se) Rules?
Volker Tresp, Hang Li, Federico Harjes +1
Although quantum systems are generally described by quantum state vectors, we show that in certain cases their measurement processes can be reformulated as probabilistic equations…
First Experience with Real-Time Control Using Simulated VQC-Based Quantum Policies
Yize Sun, Mohamad Hagog, Marc Weber +4
This paper investigates the integration of quantum computing into offline reinforcement learning and the deployment of the resulting quantum policy in a real-time control hardware…
Parameter-Efficient Routed Fine-Tuning: Mixture-of-Experts Demands Mixture of Adaptation Modules
Yilun Liu, Yunpu Ma, Yuetian Lu +3
Mixture-of-Experts (MoE) benefits from a dynamic routing mechanism among their specialized experts, which existing Parameter- Efficient Fine-Tuning (PEFT) strategies fail to levera…
SwarmAgentic: Towards Fully Automated Agentic System Generation via Swarm Intelligence
Yao Zhang, Chenyang Lin, Shijie Tang +4
The rapid progress of Large Language Models has advanced agentic systems in decision-making, coordination, and task execution. Yet, existing agentic system generation frameworks la…
FedNano: Toward Lightweight Federated Tuning for Pretrained Multimodal Large Language Models
Yao Zhang, Hewei Gao, Haokun Chen +3
Multimodal Large Language Models (MLLMs) excel in tasks like multimodal reasoning and cross-modal retrieval but face deployment challenges in real-world scenarios due to distribute…
ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM
Yujun Wang, Aniri, Jinhe Bi +2
Multimodal large language models (MLLMs) frequently hallucinate by over-committing to spurious visual cues. Prior remedies-Visual and Instruction Contrastive Decoding (VCD, ICD)-mi…
Self-Evolving Multi-Agent Systems via Textual Backpropagation
Xiaowen Ma, Yunpu Ma, Chenyang Lin +6
Leveraging multiple Large Language Models (LLMs) has proven effective for addressing complex, high-dimensional tasks, but current approaches often rely on static, manually engineer…
METok: Multi-Stage Event-based Token Compression for Efficient Long Video Understanding
Mengyue Wang, Shuo Chen, Kristian Kersting +2
Recent advances in Video Large Language Models (VLLMs) have significantly enhanced their ability to understand video content. Nonetheless, processing long videos remains challengin…
CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Process
Jinhe Bi, Danqi Yan, Yifan Wang +8
Recent Large Reasoning Models significantly improve the reasoning ability of Large Language Models by learning to reason, exhibiting the promising performance in solving complex ta…
Supposedly Equivalent Facts That Aren't? Entity Frequency in Pre-training Induces Asymmetry in LLMs
Yuan He, Bailan He, Zifeng Ding +8
Understanding and mitigating hallucinations in Large Language Models (LLMs) is crucial for ensuring reliable content generation. While previous research has primarily focused on "w…
PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection
Jinhe Bi, Aniri, Zengjie Jin +11
Visual instruction tuning adapts pre-trained Multimodal Large Language Models (MLLMs) to follow human instructions for real-world applications. However, the rapid growth of these d…
LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering
Jinhe Bi, Yujun Wang, Haokun Chen +4
Multimodal Large Language Models (MLLMs) have significantly advanced visual tasks by integrating visual representations into large language models (LLMs). The textual modality, inh…
PERFT: Parameter-Efficient Routed Fine-Tuning for Mixture-of-Expert Model
Yilun Liu, Yunpu Ma, Shuo Chen +4
The Mixture-of-Experts (MoE) paradigm has emerged as a powerful approach for scaling transformers with improved resource utilization. However, efficiently fine-tuning MoE models re…
VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs
Ruotong Liao, Max Erler, Huiyu Wang +4
In the video-language domain, recent works in leveraging zero-shot Large Language Model-based reasoning for video understanding have become competitive challengers to previous end-…
WebPilot: A Versatile and Autonomous Multi-Agent System for Web Task Execution with Strategic Exploration
Yao Zhang, Zijian Ma, Yunpu Ma +3
LLM-based autonomous agents often fail to execute complex web tasks that require dynamic interaction due to the inherent uncertainty and complexity of these environments. Existing…
DyGMamba: Efficiently Modeling Long-Term Temporal Dependency on Continuous-Time Dynamic Graphs with State Space Models
Zifeng Ding, Yifeng Li, Yuan He +5
Learning useful representations for continuous-time dynamic graphs (CTDGs) is challenging, due to the concurrent need to span long node interaction histories and grasp nuanced temp…
SA-DQAS: Self-attention Enhanced Differentiable Quantum Architecture Search
Yize Sun, Jiarui Liu, Zixin Wu +2
We introduce SA-DQAS, a novel framework that enhances Differentiable Quantum Architecture Search (DQAS) by integrating a self-attention mechanism, enabling more effective quantum c…
Differentiable Quantum Architecture Search For Job Shop Scheduling Problem
Yize Sun, Jiarui Liu, Yunpu Ma +1
The Job shop scheduling problem (JSSP) plays a pivotal role in industrial applications, such as signal processing (SP) and steel manufacturing, involving sequencing machines and jo…
Quantum Architecture Search with Unsupervised Representation Learning
Yize Sun, Zixin Wu, Volker Tresp +1
Unsupervised representation learning presents new opportunities for advancing Quantum Architecture Search (QAS) on Noisy Intermediate-Scale Quantum (NISQ) devices. QAS is designed…
zrLLM: Zero-Shot Relational Learning on Temporal Knowledge Graphs with Large Language Models
Zifeng Ding, Heling Cai, Jingpei Wu +4
Modeling evolving knowledge over temporal knowledge graphs (TKGs) has become a heated topic. Various methods have been proposed to forecast links on TKGs. Most of them are embeddin…
GraphextQA: A Benchmark for Evaluating Graph-Enhanced Large Language Models
Yuanchun Shen, Ruotong Liao, Zhen Han +2
While multi-modal models have successfully integrated information from image, video, and audio modalities, integrating graph modality into large language models (LLMs) remains unex…
GenTKG: Generative Forecasting on Temporal Knowledge Graph with Large Language Models
Ruotong Liao, Xu Jia, Yangzhe Li +2
The rapid advancements in large language models (LLMs) have ignited interest in the temporal knowledge graph (tKG) domain, where conventional embedding-based and rule-based methods…