Publications (97)
Beyond Parameter Arithmetic: Sparse Complementary Fusion for Distribution-Aware Model Merging
Weihong Lin, Lin Sun, Qilong Shi +6
Model merging has emerged as a promising paradigm for composing the capabilities of large language models by directly operating in weight space, enabling the integration of special…
LongAttn: Selecting Long-context Training Data via Token-level Attention
Longyun Wu, Dawei Zhu, Guangxiang Zhao +5
With the development of large language models (LLMs), there has been an increasing need for significant advancements in handling long contexts. To enhance long-context capabilities…
The unicyclic hypergraph with extremal spectral radius
Guanglong Yu, Lin Sun
For a consisting of a nonempty vertex set and an edge set , its $\mathcal {A}_{\mathcal{…
TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation
Lin Sun, Guangxiang Zhao, Xiaoqi Jian +18
The challenge of reducing the size of Large Language Models (LLMs) while maintaining their performance has gained significant attention. However, existing methods, such as model di…
MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation
Hao Shi, Bin Xie, Yingfei Liu +7
Temporal context is essential for robotic manipulation because such tasks are inherently non-Markovian, yet mainstream VLA models typically overlook it and struggle with long-horiz…
BPO: Revisiting Preference Modeling in Direct Preference Optimization
Lin Sun, Chuang Liu, Peng Liu +3
Direct Preference Optimization (DPO) have emerged as a popular method for aligning Large Language Models (LLMs) with human preferences. While DPO effectively preserves the relative…
FreePRM: Training Process Reward Models Without Ground Truth Process Labels
Lin Sun, Chuang Liu, Xiaofeng Ma +3
Recent advancements in Large Language Models (LLMs) have demonstrated that Process Reward Models (PRMs) play a crucial role in enhancing model performance. However, training PRMs t…
Fine-Grained Categorization via CNN-Based Automatic Extraction and Integration of Object-Level and Part-Level Features
Ting Sun, Lin Sun, Dit-Yan Yeung
Fine-grained categorization can benefit from part-based features which reveal subtle visual differences between object categories. Handcrafted features have been widely used for pa…
On Bott--Samelson rings for Coxeter groups
Tao Gui, Lin Sun, Shihao Wang +1
We study the cohomology ring of the Bott--Samelson variety. We compute an explicit presentation of this ring via Soergel's result, which implies that it is a purely combinatorial i…
Unusual destruction and enhancement of superfluidity of atomic Fermi gases by population imbalance in a one-dimensional optical lattice
Qijin Chen, Jibiao Wang, Lin Sun +1
We study the superfluid behavior of a population imbalanced ultracold atomic Fermi gases with a short range attractive interaction in a one-dimensional (1D) optical lattice, using…
VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial Attention
Shengheng Deng, Zhihao Liang, Lin Sun +1
Detecting objects from LiDAR point clouds is of tremendous significance in autonomous driving. In spite of good progress, accurate and reliable 3D detection is yet to be achieved d…
Flat band effects on the ground-state BCS-BEC crossover in atomic Fermi gases in a quasi-two-dimensional Lieb lattice
Hao Deng, Chuping Li, Yuxuan Wu +2
The ground-state superfluid behavior of ultracold atomic Fermi gases with a short-range attractive interaction in a quasi-two-dimensional Lieb lattice is studied using BCS mean-fie…
PAGE: A Position-Aware Graph-Based Model for Emotion Cause Entailment in Conversation
Xiaojie Gu, Renze Lou, Lin Sun +1
Conversational Causal Emotion Entailment (C2E2) is a task that aims at recognizing the causes corresponding to a target emotion in a conversation. The order of utterances in the co…
BEAR: Budgeted Evidence Allocation for Multi-Document Reasoning
Lin Sun, Linglin Zhang, Jingang Huang +3
We argue that multi-document reasoning is constrained not only by how much text a model can read, but also by how limited query-time evidence budget is allocated across documents a…
A note on algebraic connectivity of 2-connected graphs
Guanglong Yu, by Shuguang Guo, Lin Sun +2
Among all simple 2-connected graphs, and among all -graphs, the graphs with the minimum algebraic connectivity are completely determined, respectively.
iSeg: An Iterative Refinement-based Framework for Training-free Segmentation
Lin Sun, Jiale Cao, Jin Xie +2
Stable diffusion has demonstrated strong image synthesis ability to given text descriptions, suggesting it to contain strong semantic clue for grouping objects. The researchers hav…
Secure Hot Path Crowdsourcing with Local Differential Privacy under Fog Computing Architecture
Mengmeng Yang, Ivan Tjuawinata, Kwok Yan Lam +2
Crowdsourcing plays an essential role in the Internet of Things (IoT) for data collection, where a group of workers is equipped with Internet-connected geolocated devices to collec…
Coupled Recurrent Network (CRN)
Lin Sun, Kui Jia, Yuejia Shen +3
Many semantic video analysis tasks can benefit from multiple, heterogenous signals. For example, in addition to the original RGB input sequences, sequences of optical flow are usua…
Distributed Clustering in the Anonymized Space with Local Differential Privacy
Lin Sun, Jun Zhao, Xiaojun Ye
Clustering and analyzing on collected data can improve user experiences and quality of services in big data, IoT applications. However, directly releasing original data brings pote…
Aegis:An Advanced LLM-Based Multi-Agent for Intelligent Functional Safety Engineering
Lu Shi, Bin Qi, Jiarui Luo +5
Functional safety is a critical aspect of automotive engineering, encompassing all phases of a vehicle's lifecycle, including design, development, production, operation, and decomm…
Rf spectra and pseudogap in ultracold Fermi gases across the BCS-BEC crossover from pairing fluctuation theory
Chuping Li, Lin Sun, Kaichao Zhang +5
The pseudogap phenomenon is a hallmark of strongly interacting Fermi systems, from high-temperature superconductors to ultracold atomic gases, yet its precise origin remains debate…
Dynamic Airspace Management for UAVs in Evolving Urban Environments: Collaborative Coordination and Human Safety
Lin Sun, Yuhang Wang, Fan Meng Hong +3
The low-altitude economy is an emerging industry with significant development potential, in which the safety of unmanned aerial vehicle (UAV) operations is a critical challenge. Pa…
Spectral study of the pseudogap in unitary Fermi gases
Chuping Li, Lin Sun, Kaichao Zhang +5
The existence of a pseudogap in unitary Fermi gases has recently been established and measured experimentally [Li et al., Nature 626, 288 (2024)]. This lends strong support for the…
PathAsst: A Generative Foundation AI Assistant Towards Artificial General Intelligence of Pathology
Yuxuan Sun, Chenglu Zhu, Sunyi Zheng +6
As advances in large language models (LLMs) and multimodal techniques continue to mature, the development of general-purpose multimodal large language models (MLLMs) has surged, of…
Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows
Yilun Yao, Xinyu Tan, Chao-Hsuan Liu +9
LLM agents are increasingly deployed as executable systems that use tools, modify workspaces, and produce concrete artifacts. In such workflows, performance depends not only on the…
Enhancing Trust and Privacy in Distributed Networks: A Comprehensive Survey on Blockchain-based Federated Learning
Ji Liu, Chunlu Chen, Yu Li +5
While centralized servers pose a risk of being a single point of failure, decentralized approaches like blockchain offer a compelling solution by implementing a consensus mechanism…
BiSample: Bidirectional Sampling for Handling Missing Data with Local Differential Privacy
Lin Sun, Xiaojun Ye, Jun Zhao +2
Local differential privacy (LDP) has received much interest recently. In existing protocols with LDP guarantees, a user encodes and perturbs his data locally before sharing it to t…
TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment
Zhewen Tan, Wenhan Yu, Jianfeng Si +9
In recent years, safety risks associated with large language models have become increasingly prominent, highlighting the urgent need to mitigate the generation of toxic and harmful…
Real-Time Uncertainty Estimation in Computer Vision via Uncertainty-Aware Distribution Distillation
Yichen Shen, Zhilu Zhang, Mert R. Sabuncu +1
Calibrated estimates of uncertainty are critical for many real-world computer vision applications of deep learning. While there are several widely-used uncertainty estimation metho…
RpBERT: A Text-image Relation Propagation-based BERT Model for Multimodal NER
Lin Sun, Jiquan Wang, Kai Zhang +2
Recently multimodal named entity recognition (MNER) has utilized images to improve the accuracy of NER in tweets. However, most of the multimodal methods use attention mechanisms t…
Uncertainty Under the Curve: A Sequence-Level Entropy Area Metric for Reasoning LLM
Yongfu Zhu, Lin Sun, Guangxiang Zhao +2
In this work, we introduce Entropy Area Score (EAS), a simple yet effective metric to quantify uncertainty in the answer generation process of reasoning large language models (LLMs…
Scale-dependent force balance governs transition to the geostrophic regime in liquid metal rotating convection
Shao-Peng Yang, Lin Sun, Guang-Yu Ding +2
Rotating convection in low-Prandtl-number liquid metal drives dynamo action in the Earth's outer core and is central to planetary interior dynamics. It has been proposed that flow…
Degree conditions for spanning expansion hypertrees
Mengjiao Rao, Nicolás Sanhueza-Matamala, Lin Sun +2
The -expansion of a graph is the -uniform hypergraph obtained from by adding new vertices to every edge. We determine, for all , asymptotically op…
TACLR: A Scalable and Efficient Retrieval-based Method for Industrial Product Attribute Value Identification
Yindu Su, Huike Zou, Lin Sun +7
Product Attribute Value Identification (PAVI) involves identifying attribute values from product profiles, a key task for improving product search, recommendation, and business ana…
Expand VSR Benchmark for VLLM to Expertize in Spatial Rules
Peijin Xie, Lin Sun, Bingquan Liu +4
Distinguishing spatial relations is a basic part of human cognition which requires fine-grained perception on cross-instance. Although benchmarks like MME, MMBench and SEED compreh…
UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Models
Lin Sun, Zhiwei Guan, Conglin Wang +7
Mainstream Fast-Slow dual system vision-language-action models decouple a high-frequency action expert from a low-frequency vision-language model for efficiency, yet they face a fu…
Lattice Long Short-Term Memory for Human Action Recognition
Lin Sun, Kui Jia, Kevin Chen +3
Human actions captured in video sequences are three-dimensional signals characterizing visual appearance and motion dynamics. To learn action patterns, existing methods adopt Convo…
Effects of particle-hole fluctuations on the superfluid transition in two-dimensional atomic Fermi gases
Junru Wu, Zongpu Wang, Lin Sun +6
Proper treatment of the many-body interactions is of paramount importance in our understanding of strongly correlated systems. Here we investigate the effects of particle-hole fluc…
Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning Capabilities Through Evaluation Design
Lin Sun, Weihong Lin, Jinzhu Wu +8
Reasoning models represented by the Deepseek-R1-Distill series have been widely adopted by the open-source community due to their strong performance in mathematics, science, progra…
An integer grid bridge sampler for the Bayesian inference of incomplete birth-death records
Lin Sun, Gang Wei
A one-to-one correspondence is established between the bridge path space of birth-death processes and the exclusive union of the product spaces of simplexes and integer grids. Form…
DSSP: A Distributed, SLO-aware, Sensing-domain-privacy-Preserving Architecture for Sensing-as-a-Service
Lin Sun, Todd Rosenkrantz, Prathyusha Enganti +5
In this paper, we propose DSSP, a Distributed, SLO-aware, Sensing-domain-privacy-Preserving architecture for Sensing-as-a-Service (SaS). DSSP addresses four major limitations of th…
Petabit-per-second Random Number Generation
Lin Jiang, Jihui Sun, Qiao Zhang +14
Physical random number generators based on chaotic microcombs, with their complex nonlinear dynamics and multi-channel parallel capability, have attracted considerable research att…
On the maximum spectral radius of planar graphs
Guanglong Yu, Lin Sun
This paper investigates the maximum spectral radius of planar graphs with concrete fixed number of vertices, providing some tight bounds on the maximum spectral radius of general p…
Exchange of Perspective Prompting Enhances Reasoning in Large Language Models
Lin Sun, Can Zhang
Large language models (LLMs) have made significant advancements in addressing diverse natural language processing (NLP) tasks. However, their performance is often limited by inhere…
Probing vectorial near field of light: imaging theory and design principles of nanoprobes
Lin Sun, Benfeng Bai, Jia Wang
Near-field microscopy is widely used for characterizing electromagnetic fields at nanoscale, where nanoprobes afford the opportunity to extract subwavelength optical quantities, in…
Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots
Qi Chen, Lin Sun, Zhixin Wang +2
Accurate 3D object detection in LiDAR based point clouds suffers from the challenges of data sparsity and irregularities. Existing methods strive to organize the points regularly,…
Regularizations for shock and rarefaction waves in the perturbed solitons of the KP equation
Guangfu Han, Yuji Kodama, Chuanzhong Li +1
Using an asymptotic perturbation method, we study the initial value problem for the KP equation with initial data consisting of parts of exact line-soliton solutions. We consider a…
CLIPer: Hierarchically Improving Spatial Representation of CLIP for Open-Vocabulary Semantic Segmentation
Lin Sun, Jiale Cao, Jin Xie +2
Contrastive Language-Image Pre-training (CLIP) exhibits strong zero-shot classification ability on various image-level tasks, leading to the research to adapt CLIP for pixel-level…
Feedback Networks
Amir R. Zamir, Te-Lin Wu, Lin Sun +3
Currently, the most successful learning models in computer vision are based on learning successive representations followed by a decision layer. This is usually actualized through…
Lifting by Gaussians: A Simple, Fast and Flexible Method for 3D Instance Segmentation
Rohan Chacko, Nicolai Haeni, Eldar Khaliullin +2
We introduce Lifting By Gaussians (LBG), a novel approach for open-world instance segmentation of 3D Gaussian Splatted Radiance Fields (3DGS). Recently, 3DGS Fields have emerged as…
Quantum Geometry, Anomalous Scaling, and Strong Pseudogap Superfluidity in a Flat-Band Lieb Lattice
Hao Deng, Lin Sun, Chuping Li +6
Flat-band systems such as magic-angle twisted bilayer graphene host strong-correlation superconductivity at vanishingly weak coupling, yet how quantum geometry and pairing fluctuat…
TextlessRAG: End-to-End Visual Document RAG by Speech Without Text
Peijin Xie, Shun Qian, Bingquan Liu +3
Document images encapsulate a wealth of knowledge, while the portability of spoken queries enables broader and flexible application scenarios. Yet, no prior work has explored knowl…
BiSwift: Bandwidth Orchestrator for Multi-Stream Video Analytics on Edge
Lin Sun, Weijun Wang, Tingting Yuan +4
High-definition (HD) cameras for surveillance and road traffic have experienced tremendous growth, demanding intensive computation resources for real-time analytics. Recently, offl…
Pairing phenomena and superfluidity of atomic Fermi gases in a two-dimensional optical lattice: Unusual effects of lattice-continuum mixing
Lin Sun, Jibiao Wang, Xiang Chu +1
We study the superfluid behavior of ultracold atomic Fermi gases with a short range attractive interaction in a two-dimensional optical lattice (2DOL) using a pairing fluctuation t…
Efficient Switchable Safety Control in LLMs via Magic-Token-Guided Co-Training
Jianfeng Si, Lin Sun, Zhewen Tan +1
Current methods for content safety in Large Language Models (LLMs), such as Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF), often rely on multi-…
Large Language Models Badly Generalize across Option Length, Problem Types, and Irrelevant Noun Replacements
Guangxiang Zhao, Saier Hu, Xiaoqi Jian +5
In this paper, we propose a ``Generalization Stress Test" to assess Large Language Models' (LLMs) generalization ability under slight and controlled perturbations, including option…
Minimum degree conditions for Hamilton -cycles in -uniform hypergraphs
Jie Han, Lin Sun, Guanghui Wang
We show that for and sufficiently large , every 5-graph on vertices with contains a Hamilton 2-cycle. This minimum 2-degr…
Tiling in dense graphs
Nannan Chen, Xizhi Liu, Lin Sun +1
We determine asymptotically the two extremal constructions for the tiling problem of the -shaped tree. In particular, the first extremal construction is close to the complement…
IPG-Net: Image Pyramid Guidance Network for Small Object Detection
Ziming Liu, Guangyu Gao, Lin Sun +1
For Convolutional Neural Network-based object detection, there is a typical dilemma: the spatial information is well kept in the shallow layers which unfortunately do not have enou…
Learning Category-level Shape Saliency via Deep Implicit Surface Networks
Chaozheng Wu, Lin Sun, Xun Xu +1
This paper is motivated from a fundamental curiosity on what defines a category of object shapes. For example, we may have the common knowledge that a plane has wings, and a chair…
Probabilistic Multi-modal Trajectory Prediction with Lane Attention for Autonomous Vehicles
Chenxu Luo, Lin Sun, Dariush Dabiri +1
Trajectory prediction is crucial for autonomous vehicles. The planning system not only needs to know the current state of the surrounding objects but also their possible states in…
Conditional Analysis for Key-Value Data with Local Differential Privacy
Lin Sun, Jun Zhao, Xiaojun Ye +3
Local differential privacy (LDP) has been deemed as the de facto measure for privacy-preserving distributed data collection and analysis. Recently, researchers have extended LDP to…
Large -tilings and Hamilton -cycles in -uniform hypergraphs
Luyining Gan, Jie Han, Lin Sun +1
Let be the -uniform hypergraph with two edges intersecting in two vertices. Our main result is that any -vertex 3-uniform hypergraph with at least $\binom{n}{3} - \…
UMIE: Unified Multimodal Information Extraction with Instruction Tuning
Lin Sun, Kai Zhang, Qingyuan Li +1
Multimodal information extraction (MIE) gains significant attention as the popularity of multimedia content increases. However, current MIE methods often resort to using task-speci…
MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection
Zhewen Tan, Yilun Yao, Huiyan Jin +9
Large language model agents increasingly rely on persistent memory to store past interactions, retrieve relevant demonstrations, and improve long-horizon task execution. However, t…
Human Action Recognition using Factorized Spatio-Temporal Convolutional Networks
Lin Sun, Kui Jia, Dit-Yan Yeung +1
Human actions in video sequences are three-dimensional (3D) spatio-temporal signals characterizing both the visual appearance and motion dynamics of the involved humans and objects…
The two loop supersymmetric corrections to lepton anomalous dipole moments in split supersymmetry scenarios
Tai-Fu Feng, Lin Sun, Xiu-Yi Yang
An analysis of electroweak corrections to the anomalous dipole moments of lepton from some special two-loop diagrams where a closed neutralino/chargino loop is inserted into releva…
The threshold for powers of tight Hamilton cycles in random hypergraphs
Yulin Chang, Jie Han, Lin Sun
We investigate the occurrence of powers of tight Hamilton cycles in random hypergraphs. For every and , we show that there exists a constant such that if $…
When Do Prompt-Side Agent Playbooks Transfer? Accuracy, Cost, and Runtime Shift in Agent Deployment
Weihong Lin, Lin Sun, Xiangzheng Zhang
Prompt-side playbooks can improve tool-using language agents without retraining, but their portability beyond the source setting is unclear. We study frozen playbook transfer under…
Beyond Static Alignment: Hierarchical Policy Control for LLM Safety via Risk-Aware Chain-of-Thought
Jianfeng Si, Lin Sun, Weihong Lin +1
Large Language Models (LLMs) face a fundamental safety-helpfulness trade-off due to static, one-size-fits-all safety policies that lack runtime controllabilityxf, making it difficu…
Combinatorial Keyword Recommendations for Sponsored Search with Deep Reinforcement Learning
Zhipeng Li, Jianwei Wu, Lin Sun +1
In sponsored search, keyword recommendations help advertisers to achieve much better performance within limited budget. Many works have been done to mine numerous candidate keyword…
Experimental Demonstration of 16D Voronoi Constellation with Two-Level Coding over 50km Four-Core Fiber
Can Zhao, Bin Chen, Jiaqi Cai +7
A 16-dimensional Voronoi constellation concatenated with multilevel coding is experimentally demonstrated over a 50km four-core fiber transmission system. The proposed scheme reduc…
Electroweak and supersymmetric two-loop corrections to lepton anomalous magnetic and electric dipole moments
Tai-Fu Feng, Lin Sun, Xiu-Yi Yang
Using the effective Lagrangian method, we analyze the electroweak corrections to the anomalous dipole moments of lepton from some special two-loop diagrams where a closed neutralin…
External Experience Serving in Production LLM Systems: A Deployment-Oriented Study of Quality-Cost Trade-offs
Lin Sun, Heming Zhang, Xiangzheng Zhang
Production LLM systems accumulate reusable operational experience, but the practical deployment issue is not merely whether such experience can help. It is how different serving st…
Using EBGAN for Anomaly Intrusion Detection
Yi Cui, Wenfeng Shen, Jian Zhang +4
As an active network security protection scheme, intrusion detection system (IDS) undertakes the important responsibility of detecting network attacks in the form of malicious netw…
Chain-of-Thought Matters: Improving Long-Context Language Models with Reasoning Path Supervision
Dawei Zhu, Xiyu Wei, Guangxiang Zhao +7
Recent advances in Large Language Models (LLMs) have highlighted the challenge of handling long-context tasks, where models need to reason over extensive input contexts to aggregat…
The maximum number of two 4-vertex graphs in planar graphs
Wei Liu, Lin Sun, Jianliang Wu
Let be the maximum number of copies of a graph in a planar graph of order . When is a connected graph on four vertices, has been completely determined…
Ground states of atomic Fermi gases in a two-dimensional optical lattice with and without population imbalance
Lin Sun, Qijin Chen
We study the ground state phase diagram of population balanced and imbalanced ultracold atomic Fermi gases with a short range attractive interaction throughout the crossover from B…
When Good OCR Is Not Enough: Benchmarking OCR Robustness for Retrieval-Augmented Generation
Lin Sun, Wang Dexian, Jingang Huang +4
Industrial Retrieval-Augmented Generation (RAG) systems depend on optical character recognition (OCR) to transform visual documents into text. Existing OCR benchmarks rely on chara…
Dexbotic: Open-Source Vision-Language-Action Toolbox
Bin Xie, Erjin Zhou, Fan Jia +36
In this paper, we present Dexbotic, an open-source Vision-Language-Action (VLA) model toolbox based on PyTorch. It aims to provide a one-stop VLA research service for professionals…
Coexistence of spin glass and ferroelectricity in highly ordered Bi2FeMnO6 epitaxial thin film
Lin Sun, Yue-Wen Fang, Jun He +10
Highly ordered Bi2FeMnO6 epitaxial thin films have been successfully grown on SrTiO3 substrate. Both synchrotron X-ray reciprocal space mapping and high resolution transmission ele…
Large -tilings in 3-uniform hypergraphs
Jie Han, Lin Sun, Guanghui Wang
Let be the 3-graph with two edges intersecting in two vertices. We prove that every 3-graph on vertices with at least $ \max \left \{ \binom{4αn}{3}, \binom{…
HRDNet: High-resolution Detection Network for Small Objects
Ziming Liu, Guangyu Gao, Lin Sun +1
Small object detection is challenging because small objects do not contain detailed information and may even disappear in the deep network. Usually, feeding high-resolution images…
CaMDN: Enhancing Cache Efficiency for Multi-tenant DNNs on Integrated NPUs
Tianhao Cai, Liang Wang, Limin Xiao +4
With the rapid development of DNN applications, multi-tenant execution, where multiple DNNs are co-located on a single SoC, is becoming a prevailing trend. Although many methods ar…
GeoVLA: Empowering 3D Representations in Vision-Language-Action Models
Lin Sun, Bin Xie, Yingfei Liu +3
Vision-Language-Action (VLA) models have emerged as a promising approach for enabling robots to follow language instructions and predict corresponding actions. However, current VLA…
Competition of electronic correlation and reconstruction in La1-xSrxTiO3/SrTiO3 heterostructures
Xueyan Wang, Lin Sun, Chen Ye +10
Electronic correlation and reconstruction are two important factors that play a critical role in shaping the magnetic and electronic properties of correlated low-dimensional system…
Indeterminate Probability Theory
Tao Yang, Chuang Liu, Xiaofeng Ma +8
Complex continuous or mixed joint distributions (e.g., P(Y | z_1, z_2, ..., z_N)) generally lack closed-form solutions, often necessitating approximations such as MCMC. This paper…
Router Upcycling: Leveraging Mixture-of-Routers in Mixture-of-Experts Upcycling
Junfeng Ran, Guangxiang Zhao, Yuhan Wu +7
The Mixture-of-Experts (MoE) models have gained significant attention in deep learning due to their dynamic resource allocation and superior performance across diverse tasks. Howev…
Grasp Proposal Networks: An End-to-End Solution for Visual Learning of Robotic Grasps
Chaozheng Wu, Jian Chen, Qiaoyu Cao +4
Learning robotic grasps from visual observations is a promising yet challenging task. Recent research shows its great potential by preparing and learning from large-scale synthetic…
AeroMesa: Efficient Data Management System for Multi-Dimensional Spatio-Temporal Trajectories
Yue Zhang, Zizhong Ding, Lin Sun +3
The proliferation of multi-dimensional trajectory data, fueled by large-scale IoT and the emerging low-altitude economy, particularly UAV operations, drives repositories to jointly…
Extracting the pairing gap from van Hove singularities in rf spectra of the Fermi Hubbard model
Chuping Li, Kaichao Zhang, Junru Wu +5
We show that van Hove singularities in rf spectra of the 3D attractive Fermi Hubbard model provide a robust route to extracting the pairing gap. Four types of singularities are cla…
A Primer in Post-Training Reasoning Data: What We Know About How It Works
Yaoming Li, Guangxiang Zhao, Qilong Shi +3
Post-training has become a primary driver of recent progress in large reasoning models, and reasoning data are often the key variable determining whether this stage succeeds. Work…
Thinking with Reasoning Skills: Fewer Tokens, More Accuracy
Guangxiang Zhao, Qilong Shi, Xusen Xiao +3
Reasoning LLMs often spend substantial tokens on long intermediate reasoning traces (e.g., chain-of-thought) when solving new problems. We propose to summarize and store reusable r…
FineQ: Software-Hardware Co-Design for Low-Bit Fine-Grained Mixed-Precision Quantization of LLMs
Xilong Xie, Liang Wang, Limin Xiao +4
Large language models (LLMs) have significantly advanced the natural language processing paradigm but impose substantial demands on memory and computational resources. Quantization…
Superfluidity and pairing phenomena in ultracold atomic Fermi gases in one-dimensional optical lattices, Part II: Effects of population imbalance
Jibiao Wang, Lin Sun, Qiang Zhang +4
In this paper, we study the effect of population imbalance and its interplay with pairing strength and lattice effect in atomic Fermi gases in a one-dimensional optical lattice. We…
RealClawBench: Live OpenClaw Benchmarks from Real Developer-Agent Sessions
Zongwei Lv, Zhewen Tan, Yaoming Li +7
Agent benchmarks should reflect what users actually ask deployed agents to do, yet existing benchmarks often miss key realism properties of real developer-agent sessions. We introd…
The uniform supertrees with the extremal spectral radius
Guanglong Yu, Lin Sun
For a consisting of a nonempty vertex set and an edge set , its $\mathcal {A}_{\mathcal{…