arXiv subjects

Wei Wei

Publications and source records attributed to Wei Wei.

At least 127 records · Page 7Linked to original sources

arXiv2025

Boost of critical current density near quantum critical points in FeSe-Based superconductors with two superconducting domes

Recent studies have identified two superconducting domes in FeSe-based superconductors. It was discovered that each dome is accompanied by a distinct nematic quantum critical point (QCP): one associated with a pure nematic QCP, and the other with a nematic QCP entangled with antiferromagnetism (AFM). In this study, we delve into the evolution of the critical current density ($J_{\rm{c}}$) with doping in FeSe${_{1-x}}$(Te/S)${_{x}}$ single crystals, focusing on the behavior within the two superconducting domes. Surprisingly, three maxima of $J_{\rm{c}}$ were found in the two superconducting domes, with two sharp peaks in $J_{\rm{c}}$ observed precisely at the endpoints of the nematic phases, at $x$(Te) $\sim$ 0.5 for Te-doped and $x$(S) $\sim$ 0.17 for S-doped FeSe. The mechanisms of vortex pinning and the influence of quantum critical fluctuations have been extensively explored, emphasizing the contribution of quantum critical fluctuations in modulating $J_{\rm{c}}$. Additionally, an increase in $J_{\rm{c}}$ was also noted near FeSe$_{0.1}$Te$_{0.9}$, where its origin has been explored and discussed. This finding provides crucial clues about the existence of an ordered phase endpoint beneath the superconducting dome, offering an initial basis for further investigation into the potential presence of a QCP beneath it.

cond-mat.supr-con↗

arXiv2025

ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning

Narrative comprehension on long stories and novels has been a challenging domain attributed to their intricate plotlines and entangled, often evolving relations among characters and entities. Given the LLM's diminished reasoning over extended context and its high computational cost, retrieval-based approaches remain a pivotal role in practice. However, traditional RAG methods could fall short due to their stateless, single-step retrieval process, which often overlooks the dynamic nature of capturing interconnected relations within long-range context. In this work, we propose ComoRAG, holding the principle that narrative reasoning is not a one-shot process, but a dynamic, evolving interplay between new evidence acquisition and past knowledge consolidation, analogous to human cognition on reasoning with memory-related signals in the brain. Specifically, when encountering a reasoning impasse, ComoRAG undergoes iterative reasoning cycles while interacting with a dynamic memory workspace. In each cycle, it generates probing queries to devise new exploratory paths, then integrates the retrieved evidence of new aspects into a global memory pool, thereby supporting the emergence of a coherent context for the query resolution. Across four challenging long-context narrative benchmarks (200K+ tokens), ComoRAG outperforms strong RAG baselines with consistent relative gains up to 11% compared to the strongest baseline. Further analysis reveals that ComoRAG is particularly advantageous for complex queries requiring global context comprehension, offering a principled, cognitively motivated paradigm towards retrieval-based stateful reasoning. Our framework is made publicly available at https://github.com/EternityJune25/ComoRAG.

cs.CL↗

arXiv2025

ScaleADFG: Affordance-based Dexterous Functional Grasping via Scalable Dataset

Dexterous functional tool-use grasping is essential for effective robotic manipulation of tools. However, existing approaches face significant challenges in efficiently constructing large-scale datasets and ensuring generalizability to everyday object scales. These issues primarily arise from size mismatches between robotic and human hands, and the diversity in real-world object scales. To address these limitations, we propose the ScaleADFG framework, which consists of a fully automated dataset construction pipeline and a lightweight grasp generation network. Our dataset introduce an affordance-based algorithm to synthesize diverse tool-use grasp configurations without expert demonstrations, allowing flexible object-hand size ratios and enabling large robotic hands (compared to human hands) to grasp everyday objects effectively. Additionally, we leverage pre-trained models to generate extensive 3D assets and facilitate efficient retrieval of object affordances. Our dataset comprising five object categories, each containing over 1,000 unique shapes with 15 scale variations. After filtering, the dataset includes over 60,000 grasps for each 2 dexterous robotic hands. On top of this dataset, we train a lightweight, single-stage grasp generation network with a notably simple loss design, eliminating the need for post-refinement. This demonstrates the critical importance of large-scale datasets and multi-scale object variant for effective training. Extensive experiments in simulation and on real robot confirm that the ScaleADFG framework exhibits strong adaptability to objects of varying scales, enhancing functional grasp stability, diversity, and generalizability. Moreover, our network exhibits effective zero-shot transfer to real-world objects. Project page is available at https://sizhe-wang.github.io/ScaleADFG_webpage

cs.RO↗

arXiv2025

Bridged Semantic Alignment for Zero-shot 3D Medical Image Diagnosis

3D medical images such as computed tomography are widely used in clinical practice, offering a great potential for automatic diagnosis. Supervised learning-based approaches have achieved significant progress but rely heavily on extensive manual annotations, limited by the availability of training data and the diversity of abnormality types. Vision-language alignment (VLA) offers a promising alternative by enabling zero-shot learning without additional annotations. However, we empirically discover that the visual and textural embeddings after alignment endeavors from existing VLA methods form two well-separated clusters, presenting a wide gap to be bridged. To bridge this gap, we propose a Bridged Semantic Alignment (BrgSA) framework. First, we utilize a large language model to perform semantic summarization of reports, extracting high-level semantic information. Second, we design a Cross-Modal Knowledge Interaction module that leverages a cross-modal knowledge bank as a semantic bridge, facilitating interaction between the two modalities, narrowing the gap, and improving their alignment. To comprehensively evaluate our method, we construct a benchmark dataset that includes 15 underrepresented abnormalities as well as utilize two existing benchmark datasets. Experimental results demonstrate that BrgSA achieves state-of-the-art performances on both public benchmark datasets and our custom-labeled dataset, with significant improvements in zero-shot diagnosis of underrepresented abnormalities.

cs.CV↗

arXiv2025

DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning

Unlearning in Large Language Models (LLMs) is crucial for protecting private data and removing harmful knowledge. Most existing approaches rely on fine-tuning to balance unlearning efficiency with general language capabilities. However, these methods typically require training or access to retain data, which is often unavailable in real world scenarios. Although these methods can perform well when both forget and retain data are available, few works have demonstrated equivalent capability in more practical, data-limited scenarios. To overcome these limitations, we propose Detect-Reasoning Augmented GeneratiON (DRAGON), a systematic, reasoning-based framework that utilizes in-context chain-of-thought (CoT) instructions to guard deployed LLMs before inference. Instead of modifying the base model, DRAGON leverages the inherent instruction-following ability of LLMs and introduces a lightweight detection module to identify forget-worthy prompts without any retain data. These are then routed through a dedicated CoT guard model to enforce safe and accurate in-context intervention. To robustly evaluate unlearning performance, we introduce novel metrics for unlearning performance and the continual unlearning setting. Extensive experiments across three representative unlearning tasks validate the effectiveness of DRAGON, demonstrating its strong unlearning capability, scalability, and applicability in practical scenarios.

cs.CL↗

arXiv2025

KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse

We describe KVLink, an approach for efficient key-value (KV) cache reuse in large language models (LLMs). In many LLM applications, different inputs can share overlapping context, such as the same retrieved document appearing in multiple queries. However, the LLMs still need to encode the entire context for each query, leading to redundant computation. In this paper, we investigate a new strategy to eliminate such inefficiency, where the KV cache of each document is precomputed independently. During inference, the KV caches of retrieved documents are concatenated, allowing the model to reuse cached representations instead of recomputing them. To mitigate the performance degradation when using KV caches computed independently for each document, KVLink introduces two key techniques: adjusting positional embeddings of the KV cache at inference to match the global position after concatenation, and using trainable special tokens to restore self-attention across independently encoded documents. Experiments across 7 datasets demonstrate that KVLink improves question answering accuracy by an average of 4% over state-of-the-art methods. Furthermore, by leveraging precomputed KV caches, our approach reduces time-to-first-token by up to 96% compared to standard LLM inference, making it a scalable and efficient solution for context reuse. Additionally, KVLink can be combined with KV cache compression to further save cache loading and storage overhead while outperforming the baselines.

cs.CL↗

arXiv2025

ProRefine: Inference-Time Prompt Refinement with Textual Feedback

Agentic workflows, where multiple AI agents collaborate to accomplish complex tasks like reasoning or planning, play a substantial role in many cutting-edge commercial applications, and continue to fascinate researchers across fields for their potential to accomplish expensive, complex tasks that, until recently, only humans have been trusted to do. These workflows depend critically on the prompts used to provide the roles models play in such workflows. Poorly designed prompts that fail even slightly to guide individual agents can lead to sub-optimal performance that may snowball within a system of agents, limiting their reliability and scalability. To address this important problem of inference-time prompt optimization, we introduce ProRefine, an innovative inference-time optimization method that uses an agentic loop of LLMs to generate and apply textual feedback. ProRefine dynamically refines prompts for multi-step reasoning tasks without additional training or ground truth labels. Evaluated on five benchmark mathematical reasoning datasets, ProRefine significantly surpasses zero-shot Chain-of-Thought baselines by 3 to 37 percentage points. This approach not only boosts accuracy but also allows smaller models to approach the performance of their larger counterparts. This highlights its potential for building more cost-effective and powerful hybrid AI systems, thereby democratizing access to high-performing AI.

cs.CL↗

arXiv2025

Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization

Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs). However, standard RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions. In this work, we reinterpret RAG as Retrieval-Augmented Reasoning and identify a central but underexplored problem: Reasoning Misalignment -- the divergence between an LLM's internal reasoning trajectory and the evidential constraints provided by retrieval. To address this issue, we propose AlignRAG, a novel iterative framework grounded in Critique-Driven Alignment (CDA). We further introduce AlignRAG-auto, an autonomous variant that dynamically terminates refinement, removing the need to pre-specify the number of critique iterations. At the heart of AlignRAG lies a contrastive critique synthesis mechanism that generates retrieval-sensitive critiques while mitigating self-bias. This mechanism trains a dedicated retrieval-augmented Critic Language Model (CLM) using labeled critiques that distinguish between evidence-aligned and misaligned reasoning. Empirical evaluations show that our approach significantly improves reasoning fidelity. Our 8B-parameter CLM improves performance over the Self-Refine baseline by 12.1% on out-of-domain tasks and outperforms a standard 72B-parameter CLM by 2.2%. Furthermore, AlignRAG-auto achieves this state-of-the-art performance while dynamically determining the optimal number of refinement steps, enhancing efficiency and usability. AlignRAG remains compatible with existing RAG architectures as a plug-and-play module and demonstrates strong robustness under both informative and noisy retrieval scenarios.

cs.AI↗

arXiv2025

WebDART: Dynamic Decomposition and Re-planning for Complex Web Tasks

Large language model (LLM) agents are becoming competent at straightforward web tasks, such as opening an item page or submitting a form, but still struggle with objectives that require long horizon navigation, large scale information extraction, and reasoning under constraints. We present WebDART, a general framework that enables a single LLM to handle such complex chores. WebDART (i) dynamically decomposes each objective into three focused subtasks: navigation, information extraction, and execution, so the model concentrates on one skill at a time, and (ii) continuously replans the decomposition as new webpages are revealed, taking advantage of newly discovered filters or shortcuts and avoiding redundant exploration. Evaluated on WebChoreArena, WebDART lifts success rates by up to 13.7 percentage points over previous SOTA agents, while matching their performance on the easier WebArena suite and completing tasks with up to 14.7 fewer navigation steps.

cs.AI↗

arXiv2025

Automated Risk Management Mechanisms in DeFi Lending Protocols: A Crosschain Comparative Analysis of Aave and Compound

Blockchain-based decentralised lending is a rapidly growing and evolving alternative to traditional lending, but it poses new risks. To mitigate these risks, lending protocols have integrated automated risk management tools into their smart contracts. However, the effectiveness of the latest risk management features introduced in the most recent versions of these lending protocols is understudied. To close this gap, we use a panel regression fixed effects model to empirically analyse the cross-version (v2 and v3) and cross-chain (L1 and L2) effectiveness of liquidation mechanisms, measured through TVL and total revenue as proxies for performance of the two most popular lending protocols, Aave and Compound, during the period Jan 2021 to Dec 2024. Our analysis reveals that liquidation events in v3 of both protocols lead to an increase in total value locked and total revenue, with stronger impact on the L2 blockchain compared to L1. In contrast, liquidations in v2 have an insignificant impact, which indicates that the most recent v3 protocols have better risk management than the earlier v2 protocols. We also show that L1 blockchains are the preferred choice among large investors for their robust liquidity and ecosystem depth, while L2 blockchains are more popular among retail investors for their lower fees and faster execution.

q-fin.RM↗

arXiv2025

Synchronization of stochastic dissipative differential equation driven by fractional Brownian motions

In this paper, we study a class of dissipative stochastic differential equations driven by nonlinear multiplicative fractional Brownian noise with Hurst index $H \in \left(\frac{1}{3},\frac{1}{2})\cup(\frac{1}{2}, 1\right) $. We establish the well-posedness of the associated coupled stochastic differential equations and prove synchronization in the sense of trajectories. Our approach relies on the Doss-Sussmann transformation, which enables us to extend existing results for additive and linear noise to the case of nonlinear multiplicative fractional Brownian noise. The findings provide new insights into the synchronization of dissipative systems under fractional noise perturbations.

math.PR↗

arXiv2025

On the vanishing viscosity limit for incompressible flows with inflow/outflow boundary conditions

We study the vanishing viscosity limit for the incompressible Navier-Stokes equations (NSE) in a general bounded domain with inflow-outflow boundary conditions. Extending the work of Gie, Hamouda, and Temam ( Netw. Heterog. Media 7, 2012) and also of Lombardo and Sammartino (SIAM J. Math. Anal. 33, 2001), we allow for a general injection and suction angle, as long as it is bounded away from zero. We rigorously establish the convergence of NSE solutions to those of the Euler equations (EE) as viscosity vanishes in the energy norm. We prove interior convergence in both the $L^2$ and the Sobolev $H^1$ norms at the same rates as in the case of injection/suction normal to the boundary. The proof relies on the construction of boundary layer correctors via Prandtl-type equations and a higher-order asymptotic expansion that improves the convergence rate.

math.AP↗

arXiv2025

UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generation

High-fidelity 3D asset generation is crucial for various industries. While recent 3D pretrained models show strong capability in producing realistic content, most are built upon diffusion models and follow a two-stage pipeline that first generates geometry and then synthesizes appearance. Such a decoupled design tends to produce geometry-texture misalignment and non-negligible cost. In this paper, we propose UniLat3D, a unified framework that encodes geometry and appearance in a single latent space, enabling direct single-stage generation. Our key contribution is a geometry-appearance Unified VAE, which compresses high-resolution sparse features into a compact latent representation -- UniLat. UniLat integrates structural and visual information into a dense low-resolution latent, which can be efficiently decoded into diverse 3D formats, e.g., 3D Gaussians and meshes. Based on this unified representation, we train a single flow-matching model to map Gaussian noise directly into UniLat, eliminating redundant stages. Trained solely on public datasets, UniLat3D produces high-quality 3D assets in seconds from a single image, achieving superior appearance fidelity and geometric quality. More demos \& code are available at https://unilat3d.github.io/

cs.CV↗

arXiv2025

Goal-Guided Efficient Exploration via Large Language Model in Reinforcement Learning

Real-world decision-making tasks typically occur in complex and open environments, posing significant challenges to reinforcement learning (RL) agents' exploration efficiency and long-horizon planning capabilities. A promising approach is LLM-enhanced RL, which leverages the rich prior knowledge and strong planning capabilities of LLMs to guide RL agents in efficient exploration. However, existing methods mostly rely on frequent and costly LLM invocations and suffer from limited performance due to the semantic mismatch. In this paper, we introduce a Structured Goal-guided Reinforcement Learning (SGRL) method that integrates a structured goal planner and a goal-conditioned action pruner to guide RL agents toward efficient exploration. Specifically, the structured goal planner utilizes LLMs to generate a reusable, structured function for goal generation, in which goals are prioritized. Furthermore, by utilizing LLMs to determine goals' priority weights, it dynamically generates forward-looking goals to guide the agent's policy toward more promising decision-making trajectories. The goal-conditioned action pruner employs an action masking mechanism that filters out actions misaligned with the current goal, thereby constraining the RL agent to select goal-consistent policies. We evaluate the proposed method on Crafter and Craftax-Classic, and experimental results demonstrate that SGRL achieves superior performance compared to existing state-of-the-art methods.

cs.LG↗

arXiv2025

The CEPC Clock Issue and Finetuning of the Circumference

The CEPC clock issue is related with the RF frequency coordination between the various accelerator systems and may affect the operation modes of both the accelerator and the detector. The timing structure of CEPC has been restudied with the collaboration of the accelerator team and the detector team. After discussions between two sides, the CEPC bunch structure is set such that the spacings between adjacent bunches in any CEPC operation mode are integer numbers of 23.08 ns. The master CEPC clock will be provided by the accelerator to the detector systems with a frequency of 43.33 MHz, synchronous to the beam. The CEPC detector system relies on the clock to sample physics signal at the right time. It was found that if the circumference of CEPC is slightly changed to 99955.418 m, not only is the orbit length closer to 100 km, but also the detector would benefit more for the first 10-year operation.

physics.acc-ph↗

arXiv2025

Pipelining Split Learning in Multi-hop Edge Networks

To support large-scale model training, split learning (SL) enables multiple edge devices/servers to share the intensive training workload. However, most existing works on SL focus solely on two-tier model splitting. Moreover, while some recent works have investigated the model splitting and placement problems for multi-hop SL, these solutions fail to overcome the resource idleness issue, resulting in significant network idle time. In this work, we propose a pipelined SL scheme by addressing the joint optimization problem of model splitting and placement (MSP) in multi-hop edge networks. By applying pipeline parallelism to SL, we identify that the MSP problem can be mapped to a problem of minimizing the weighted sum of a bottleneck cost function (min-max) and a linear cost function (min-sum). Based on graph theory, we devise a bottleneck-aware shortest-path algorithm to obtain the optimal solution. Besides, given the MSP outcomes, we also derive the closed-form solution to the micro-batch size in the pipeline. Finally, we develop an alternating optimization algorithm of MSP and micro-batch size to solve the joint optimization problem to minimize the end-to-end training latency. Extensive simulations have demonstrated the significant advantages of our algorithm compared to existing benchmarks without pipeline parallelism.

cs.NI↗

arXiv2025

More performant and scalable: Rethinking contrastive vision-language pre-training of radiology in the LLM era

The emergence of Large Language Models (LLMs) presents unprecedented opportunities to revolutionize medical contrastive vision-language pre-training. In this paper, we show how LLMs can facilitate large-scale supervised pre-training, thereby advancing vision-language alignment. We begin by demonstrate that modern LLMs can automatically extract diagnostic labels from radiology reports with remarkable precision (>96\% AUC in our experiments) without complex prompt engineering, enabling the creation of large-scale "silver-standard" datasets at a minimal cost (~\$3 for 50k CT image-report pairs). Further, we find that vision encoder trained on this "silver-standard" dataset achieves performance comparable to those trained on labels extracted by specialized BERT-based models, thereby democratizing the access to large-scale supervised pre-training. Building on this foundation, we proceed to reveal that supervised pre-training fundamentally improves contrastive vision-language alignment. Our approach achieves state-of-the-art performance using only a 3D ResNet-18 with vanilla CLIP training, including 83.8\% AUC for zero-shot diagnosis on CT-RATE, 77.3\% AUC on RAD-ChestCT, and substantial improvements in cross-modal retrieval (MAP@50=53.7\% for image-image, Recall@100=52.2\% for report-image). These results demonstrate the potential of utilizing LLMs to facilitate {\bf more performant and scalable} medical AI systems. Our code is avaiable at https://github.com/SadVoxel/More-performant-and-scalable.

cs.CV↗

arXiv2025

On anisotropic energy conservation criteria of incompressible fluids

In this paper, by means of divergence-free condition, we establish an anisotropic energy conservation class enabling one component of velocity in the largest space $L^{3} (0,T; B^{1/3}_{3,\infty})$ for the 3D inviscid incompressible fluids, which extends the celebrated result obtained by Cheskidov, Constantin, Friedlander and Shvydkoy in [15, Nonlinearity 21 (2008)]. For viscous flows, we generalize famous Lions's energy conservation criteria to allow the horizontal components and vertical part of velocity to have different integrability.

math.AP↗