Searcharxiv⌕ Search

arXiv subjects

Zhipeng Wang

Publications and source records attributed to Zhipeng Wang.

At least 55 records · Page 3Linked to original sources
arXiv2026

Bridging Restoration and Diagnosis: A Comprehensive Benchmark for Retinal Fundus Enhancement

Over the past decade, generative models have demonstrated success in enhancing fundus images. However, the evaluation of these models remains a challenge. A benchmark for fundus image enhancement is needed for three main reasons:(1) Conventional denoising metrics such as PSNR and SSIM fail to capture clinically relevant features, such as lesion preservation and vessel morphology consistency, limiting their applicability in real-world settings; (2) There is a lack of unified evaluation protocols that address both paired and unpaired enhancement methods, particularly those guided by clinical expertise; and (3) An evaluation framework should provide actionable insights to guide future advancements in clinically aligned enhancement models. To address these gaps, we introduce EyeBench-V2, a benchmark designed to bridge the gap between enhancement model performance and clinical utility. Our work offers three key contributions:(1) Multi-dimensional clinical-alignment through downstream evaluations: Beyond standard enhancement metrics, we assess performance across clinically meaningful tasks including vessel segmentation, diabetic retinopathy (DR) grading, generalization to unseen noise patterns, and lesion segmentation. (2) Expert-guided evaluation design: We curate a novel dataset enabling fair comparisons between paired and unpaired enhancement methods, accompanied by a structured manual assessment protocol by medical experts, which evaluates clinically critical aspects such as lesion structure alterations, background color shifts, and the introduction of artificial structures. (3) Actionable insights: Our benchmark provides a rigorous, task-oriented analysis of existing generative models, equipping clinical researchers with the evidence needed to make informed decisions, while also identifying limitations in current methods to inform the design of next-generation enhancement models.

cs.CV↗
arXiv2026

Your Agent is More Brittle Than You Think: Uncovering Indirect Injection Vulnerabilities in Agentic LLMs

The rapid deployment of open-source frameworks has significantly advanced the development of modern multi-agent systems. However, expanded action spaces, including uncontrolled privilege exposure and hidden inter-system interactions, pose severe security challenges. Specifically, Indirect Prompt Injections (IPI), which conceal malicious instructions within third-party content, can trigger unauthorized actions such as data exfiltration during normal operations. While current security evaluations predominantly rely on isolated single-turn benchmarks, the systemic vulnerabilities of these agents within complex dynamic environments remain critically underexplored. To bridge this gap, we systematically evaluate six defense strategies against four sophisticated IPI attack vectors across nine LLM backbones. Crucially, we conduct our evaluation entirely within dynamic multi-step tool-calling environments to capture the true attack surface of modern autonomous agents. Moving beyond binary success rates, our multidimensional analysis reveals a pronounced fragility. Advanced injections successfully bypass nearly all baseline defenses, and some surface-level mitigations even produce counterproductive side effects. Furthermore, while agents execute malicious instructions almost instantaneously, their internal states exhibit abnormally high decision entropy. Motivated by this latent hesitation, we investigate Representation Engineering (RepE) as a robust detection strategy. By extracting hidden states at the tool-input position, we revealed that the RepE-based circuit breaker successfully identifies and intercepts unauthorized actions before the agent commits to them, achieving high detection accuracy across diverse LLM backbones. This study exposes the limitations of current IPI defenses and provides a highly practical paradigm for building resilient multi-agent architectures.

cs.CL↗
arXiv2026

OTPrune: Distribution-Aligned Visual Token Pruning via Optimal Transport

Multi-modal large language models (MLLMs) achieve strong visual-language reasoning but suffer from high inference cost due to redundant visual tokens. Recent work explores visual token pruning to accelerate inference, while existing pruning methods overlook the underlying distributional structure of visual representations. We propose OTPrune, a training-free framework that formulates pruning as distribution alignment via optimal transport (OT). By minimizing the 2-Wasserstein distance between the full and pruned token distributions, OTPrune preserves both local diversity and global representativeness while reducing inference cost. Moreover, we derive a tractable submodular objective that enables efficient optimization, and theoretically prove its monotonicity and submodularity, providing a principled foundation for stable and efficient pruning. We further provide a comprehensive analysis that explains how distributional alignment contributes to stable and semantically faithful pruning. Comprehensive experiments on wider benchmarks demonstrate that OTPrune achieves superior performance-efficiency tradeoffs compared to state-of-the-art methods. The code is available at https://github.com/xiwenc1/OTPrune.

cs.CV↗
arXiv2026

Robust Batch-Level Query Routing for Large Language Models under Cost and Capacity Constraints

We study the problem of routing queries to large language models (LLMs) under cost, GPU resources, and concurrency constraints. Prior per-query routing methods often fail to control batch-level cost, especially under non-uniform or adversarial batching. To address this, we propose a batch-level, resource-aware routing framework that jointly optimizes model assignment for each batch while respecting cost and model capacity limits. We further introduce a robust variant that accounts for uncertainty in predicted LLM performance, along with an offline instance allocation procedure that balances quality and throughput across multiple models. Experiments on two multi-task LLM benchmarks show that robustness improves accuracy by 1-14% over non-robust counterparts (depending on the performance estimator), batch-level routing outperforms per-query methods by up to 24% under adversarial batching, and optimized instance allocation yields additional gains of up to 3% compared to a non-optimized allocation, all while strictly controlling cost and GPU resource constraints.

cs.LG↗
arXiv2026

A Tactile-based Interactive Motion Planner for Robots in Unknown Cluttered Environments

In unknown cluttered environments with densely stacked objects, the free-motion space is extremely barren, posing significant challenges to motion planners. Collision-free planning methods often suffer from catastrophic failures due to unexpected collisions and motion obstructions. To address this issue, this paper proposes an interactive motion planning framework (I-MP), based on a perception-motion loop. This framework empowers robots to autonomously model and reason about contact models, which in turn enables safe expansion of the free-motion space. Specifically, the robot utilizes multimodal tactile perception to acquire stimulus-response signal pairs. This enables real-time identification of objects' mechanical properties and the subsequent construction of contact models. These models are integrated as computational constraints into a reactive planner. Based on fixed-point theorems, the planner computes the spatial state toward the target in real time, thus avoiding the computational burden associated with extrapolating on high-dimensional interaction models. Furthermore, high-dimensional interaction features are linearly superposed in Cartesian space in the form of energy, and the controller achieves trajectory tracking by solving the energy gradient from the current state to the planned state. The experimental results showed that at cruising speeds ranging from 0.01 to 0.07 $m/s$, the robot's initial contact force with objects remained stable at 1.0 +- 0.7 N. In the cabinet scenario test where collision-free trajectories were unavailable, I-MP expanded the free motion space by 37.5 % through active interaction, successfully completing the environmental exploration task.

cs.RO↗
arXiv2026

In the Margins: An Empirical Study of Ethereum Inscriptions

Ethereum Inscriptions (Ethscriptions) repurpose Ethereum calldata into a persistent inscription channel by embedding \texttt{data:}~URI payloads. These transactions typically target externally owned accounts, allowing the payload to bypass EVM execution while remaining permanently replicated across full nodes. Although calldata was originally designed for compact smart-contract parameters, this repurposing enables structured data embedding with long-term storage consequences. We present the first large-scale empirical study of Ethscriptions, treating them as a distinct \emph{calldata-resident workload} rather than merely a subset of general calldata usage. Our analysis focuses on the \textit{Ethscription} operational subset, which consists of payloads that decode to JSON and conform to a token-operation grammar (e.g., \texttt{p}, \texttt{op}, \texttt{tick}, \texttt{amt}). From $6.27$ million Ethscription candidates (\Uone), we extract $4.75$ million Ethscription operations (\Utwo, $75.8\%$ of \Uone). This result shows that structured token-like activity dominates the ecosystem. Our measurements further reveal (i) a complete workload lifecycle compressed into nine months (bootstrap, expansion, saturation), (ii) proliferation of $30$+ competing protocols without convergence toward a dominant standard, (iii) a lifecycle funnel exhibiting $201\times$ deploy-to-mint amplification and a $57.6{:}1$ mint-to-transfer collapse indicative of speculative minting, (iv) extreme participation inequality (Gini~$0.86$), and (v) a measurable permanent data footprint imposed on the Ethereum network.

cs.CE↗
arXiv2026

Autonomous UAV-Quadruped Docking in Complex Terrains via Active Posture Alignment and Constraint-Aware Control

Autonomous docking between Unmanned Aerial Vehicles (UAVs) and ground robots is essential for heterogeneous systems, yet most existing approaches target wheeled platforms whose limited mobility constrains exploration in complex terrains. Quadruped robots offer superior adaptability but undergo frequent posture variations, making it difficult to provide a stable landing surface for UAVs. To address these challenges, we propose an autonomous UAV-quadruped docking framework for GPS-denied environments. On the quadruped side, a Hybrid Internal Model with Horizontal Alignment (HIM-HA), learned via deep reinforcement learning, actively stabilizes the torso to provide a level platform. On the UAV side, a three-phase strategy is adopted, consisting of long-range acquisition with a median-filtered YOLOv8 detector, close-range tracking with a constraint-aware controller that integrates a Nonsingular Fast Terminal Sliding Mode Controller (NFTSMC) and a logarithmic Barrier Function (BF) to guarantee finite-time error convergence under field-of-view (FOV) constraints, and terminal descent guided by a Safety Period (SP) mechanism that jointly verifies tracking accuracy and platform stability. The proposed framework is validated in both simulation and real-world scenarios, successfully achieving docking on outdoor staircases higher than 17 cm and rough slopes steeper than 30 degrees. Supplementary materials and videos are available at: https://uav-quadruped-docking.github.io.

cs.RO↗
arXiv2026

Dual-Horizon Hybrid Internal Model for Low-Gravity Quadrupedal Jumping with Hardware-in-the-Loop Validation

Locomotion under reduced gravity is commonly realized through jumping, yet continuous pronking in lunar gravity remains challenging due to prolonged flight phases and sparse ground contact. The extended aerial duration increases landing impact sensitivity and makes stable attitude regulation over rough planetary terrain difficult. Existing approaches primarily address single jumps on flat surfaces and lack both continuous-terrain solutions and realistic hardware validation. This work presents a Dual-Horizon Hybrid Internal Model for continuous quadrupedal jumping under lunar gravity using proprioceptive sensing only. Two temporal encoders capture complementary time scales: a short-horizon branch models rapid vertical dynamics with explicit vertical velocity estimation, while a long-horizon branch models horizontal motion trends and center-of-mass height evolution across the jump cycle. The fused representation enables stable and continuous jumping under extended aerial phases characteristic of lunar gravity. To provide hardware-in-the-loop validation, we develop the MATRIX (Mixed-reality Adaptive Testbed for Robotic Integrated eXploration) platform, a digital-twin-driven system that offloads gravity through a pulley-counterweight mechanism and maps Unreal Engine lunar terrain to a motion platform and treadmill in real time. Using MATRIX, we demonstrate continuous jumping of a quadruped robot under lunar-gravity emulation across cratered lunar-like terrain.

cs.RO↗
arXiv2026

DuaLip-GPU Technical Report

Large-scale linear programs (LPs) arise in many decision systems, including ranking, allocation, and matching problems that must be solved repeatedly at massive scale. Prior work such as ECLIPSE and LinkedIn's open-source DuaLip showed that ridge-regularized dual ascent with first-order methods can scale to these settings. However, the original implementation was tightly coupled to a small number of schemas and built on a CPU-centric Scala/Spark stack, limiting extensibility and preventing effective use of modern accelerators. We present a redesigned solver architecture that decouples problem specification from the optimization engine and targets GPU execution. The system uses an operator-centric programming model in which LP formulations are expressed through composable primitives for dual objective evaluation and blockwise projection operators for decomposable constraint families. This design allows new formulations to be added locally while reusing a shared optimization loop, diagnostics, and distributed infrastructure. To realize the available parallelism, we develop GPU execution techniques tailored to sparse matching constraints, including constraint-aligned sparse layouts, batched projection kernels, and a distributed design that communicates only dual variables. Further, we improve the underlying ridge-regularized dual ascent method with Jacobi-style row normalization, primal scaling, and a continuation scheme for the regularization parameter. On extreme-scale matching workloads, the GPU implementation achieves at least a 10x wall-clock speedup over the prior distributed CPU DuaLip solver under matched stopping criteria, while maintaining convergence guarantees.

cs.DC↗
arXiv2026

LLaDA-MedV: Exploring Large Language Diffusion Models for Biomedical Image Understanding

Autoregressive models (ARMs) have long dominated the landscape of biomedical vision-language models (VLMs). Recently, masked diffusion models such as LLaDA have emerged as promising alternatives, yet their application in the biomedical domain remains largely underexplored. To bridge this gap, we introduce LLaDA-MedV, the first large language diffusion model tailored for biomedical image understanding through vision instruction tuning. LLaDA-MedV achieves relative performance gains of 7.855% over LLaVA-Med and 1.867% over LLaDA-V in the open-ended biomedical visual conversation task, and sets new state-of-the-art accuracy on the closed-form subset of three VQA benchmarks: 84.93% on VQA-RAD, 92.31% on SLAKE, and 95.15% on PathVQA. Furthermore, a detailed comparison with LLaVA-Med suggests that LLaDA-MedV is capable of generating reasonably longer responses by explicitly controlling response length, which can lead to more informative outputs. We also conduct an in-depth analysis of both the training and inference stages, highlighting the critical roles of initialization weight selection, fine-tuning strategies, and the interplay between sampling steps and response repetition. The code and model weight is released at https://github.com/LLM-VLM-GSL/LLaDA-MedV.

cs.CV↗
arXiv2026

Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning

Reinforcement Learning with Verifiable Rewards (RLVR) has become the leading paradigm for enhancing reasoning in Large Language Models (LLMs). However, standard RLVR algorithms suffer from a well-documented pathology: while they improve Pass@1 accuracy through sharpened sampling, they simultaneously narrow the model's reasoning boundary and reduce generation diversity. We identify a root cause that existing methods overlook: the uniform penalization of errors. Current approaches -- whether data-filtering methods that select prompts by difficulty, or advantage normalization schemes -- treat all incorrect rollouts within a group identically. We show that this uniformity allows overconfident errors (incorrect reasoning paths that the RL process has spuriously reinforced) to persist and monopolize probability mass, ultimately suppressing valid exploratory trajectories. To address this, we propose the Asymmetric Confidence-aware Error Penalty (ACE). ACE introduces a per-rollout confidence shift metric, c_i = log(pi_theta(y_i|x) / pi_ref(y_i|x)), to dynamically modulate negative advantages. Theoretically, we demonstrate that ACE's gradient can be decomposed into the gradient of a selective regularizer restricted to overconfident errors, plus a well-characterized residual that partially moderates the regularizer's strength. We conduct extensive experiments fine-tuning Qwen2.5-Math-7B, Qwen3-8B-Base, and Llama-3.1-8B-Instruct on the DAPO-Math-17K dataset using GRPO and DAPO within the VERL framework. Evaluated on MATH-500 and AIME 2025, ACE composes seamlessly with existing methods and consistently improves the full Pass@k spectrum across all three model families and benchmarks.

cs.LG↗
arXiv2026

Not all tokens are needed(NAT): token efficient reinforcement learning

Reinforcement learning (RL) has become a key driver of progress in large language models, but scaling RL to long chain-of-thought (CoT) trajectories is increasingly constrained by backpropagation over every generated token. Even with optimized rollout engines, full-token updates can consume a large fraction of total training cost, turning token length into a hidden tax on RL. We introduce Not All Tokens Are Needed (NAT), a unified framework that makes the token budget a first-class optimization primitive. NAT updates the policy using only a selected subset of generated tokens while preserving the learning signal of full-sequence RL. The core idea is an unbiased partial-token policy-gradient estimator via Horvitz-Thompson reweighting, which ensures statistically correct gradients despite subsampling. We instantiate NAT with two simple, plug-and-play token selection schemes: Uniform Random Sampling (URS) and Random Prefix Cutting (RPC), both of which reduce forward and backward compute and memory without modifying the reward computation or rollout pipeline. Across mathematical reasoning benchmarks, NAT matches full-token GRPO performance while using as few as 50% of tokens, providing an efficient and orthogonal pathway to scaling RL beyond the limits imposed by long trajectories. In our experiments, RPC saves 18% peak GPU memory and 29% forward and backward RL training time for Qwen3-8B.

cs.LG↗
arXiv2026

Morphogenetic Assembly and Adaptive Control for Heterogeneous Modular Robots

This paper presents a closed-loop automation framework for heterogeneous modular robots, covering the full pipeline from morphological construction to adaptive control. In this framework, a mobile manipulator handles heterogeneous functional modules including structural, joint, and wheeled modules to dynamically assemble diverse robot configurations and provide them with immediate locomotion capability. To address the state-space explosion in large-scale heterogeneous reconfiguration, we propose a hierarchical planner: the high-level planner uses a bidirectional heuristic search with type-penalty terms to generate module-handling sequences, while the low level planner employs A* search to compute optimal execution trajectories. This design effectively decouples discrete configuration planning from continuous motion execution. For adaptive motion generation of unknown assembled configurations, we introduce a GPU accelerated Annealing-Variance Model Predictive Path Integral (MPPI) controller. By incorporating a multi stage variance annealing strategy to balance global exploration and local convergence, the controller enables configuration-agnostic, real-time motion control. Large scale simulations show that the type-penalty term is critical for planning robustness in heterogeneous scenarios. Moreover, the greedy heuristic produces plans with lower physical execution costs than the Hungarian heuristic. The proposed annealing-variance MPPI significantly outperforms standard MPPI in both velocity tracking accuracy and control frequency, achieving real time control at 50 Hz. The framework validates the full-cycle process, including module assembly, robot merging and splitting, and dynamic motion generation.

cs.RO↗
arXiv2026

SoK: Blockchain-Based Decentralized AI (DeAI)

Centralization enhances the efficiency of Artificial Intelligence (AI) but also introduces critical challenges, including single points of failure, inherent biases, data privacy risks, and scalability limitations. To address these issues, blockchain-based Decentralized Artificial Intelligence (DeAI) has emerged as a promising paradigm that leverages decentralization and transparency to improve the trustworthiness of AI systems. Despite rapid adoption in industry, the academic community lacks a systematic analysis of DeAI's technical foundations, opportunities, and challenges. This work presents the first Systematization of Knowledge (SoK) on DeAI, offering a formal definition, a taxonomy of existing solutions based on the AI lifecycle, and an in-depth investigation of the roles of blockchain in enabling secure and incentive-compatible collaboration. We further review security risks across the DeAI lifecycle and empirically evaluate representative mitigation techniques. Finally, we highlight open research challenges and future directions for advancing blockchain-based DeAI.

cs.LG↗
arXiv2026

Semantic Search At LinkedIn

Semantic search with large language models (LLMs) enables retrieval by meaning rather than keyword overlap, but scaling it requires major inference efficiency advances. We present LinkedIn's LLM-based semantic search framework for AI Job Search and AI People Search, combining an LLM relevance judge, embedding-based retrieval, and a compact Small Language Model trained via multi-teacher distillation to jointly optimize relevance and engagement. A prefill-oriented inference architecture co-designed with model pruning, context compression, and text-embedding hybrid interactions boosts ranking throughput by over 75x under a fixed latency constraint while preserving near-teacher-level NDCG, enabling one of the first production LLM-based ranking systems with efficiency comparable to traditional approaches and delivering significant gains in quality and user engagement.

cs.IR↗
arXiv2026

AriadneMem: Threading the Maze of Lifelong Memory for LLM Agents

Long-horizon LLM agents require memory systems that remain accurate under fixed context budgets. However, existing systems struggle with two persistent challenges in long-term dialogue: (i) \textbf{disconnected evidence}, where multi-hop answers require linking facts distributed across time, and (ii) \textbf{state updates}, where evolving information (e.g., schedule changes) creates conflicts with older static logs. We propose AriadneMem, a structured memory system that addresses these failure modes via a decoupled two-phase pipeline. In the \textbf{offline construction phase}, AriadneMem employs \emph{entropy-aware gating} to filter noise and low-information message before LLM extraction and applies \emph{conflict-aware coarsening} to merge static duplicates while preserving state transitions as temporal edges. In the \textbf{online reasoning phase}, rather than relying on expensive iterative planning, AriadneMem executes \emph{algorithmic bridge discovery} to reconstruct missing logical paths between retrieved facts, followed by \emph{single-call topology-aware synthesis}. On LoCoMo experiments with GPT-4o, AriadneMem improves \textbf{Multi-Hop F1 by 15.2\%} and \textbf{Average F1 by 9.0\%} over strong baselines. Crucially, by offloading reasoning to the graph layer, AriadneMem reduces \textbf{total runtime by 77.8\%} using only \textbf{497} context tokens. The code is available at https://github.com/LLM-VLM-GSL/AriadneMem.

cs.CL↗
arXiv2026

Scaling In-Context Online Learning Capability of LLMs via Cross-Episode Meta-RL

Large language models (LLMs) achieve strong performance when all task-relevant information is available upfront, as in static prediction and instruction-following problems. However, many real-world decision-making tasks are inherently online: crucial information must be acquired through interaction, feedback is delayed, and effective behavior requires balancing information collection and exploitation over time. While in-context learning enables adaptation without weight updates, existing LLMs often struggle to reliably leverage in-context interaction experience in such settings. In this work, we show that this limitation can be addressed through training. We introduce ORBIT, a multi-task, multi-episode meta-reinforcement learning framework that trains LLMs to learn from interaction in context. After meta-training, a relatively small open-source model (Qwen3-14B) demonstrates substantially improved in-context online learning on entirely unseen environments, matching the performance of GPT-5.2 and outperforming standard RL fine-tuning by a large margin. Scaling experiments further reveal consistent gains with model size, suggesting significant headroom for learn-at-inference-time decision-making agents. Code reproducing the results in the paper can be found at https://github.com/XiaofengLin7/ORBIT.

cs.AI↗
arXiv2026

MixLM: High-Throughput and Effective LLM Ranking via Text-Embedding Mix-Interaction

Large language models (LLMs) excel at capturing semantic nuances and therefore show impressive relevance ranking performance in modern recommendation and search systems. However, they suffer from high computational overhead under industrial latency and throughput requirements. In particular, cross-encoder ranking systems often create long context prefill-heavy workloads, as the model has to be presented with the user, query and item information. To this end, we propose MixLM, a novel LLM-based ranking framework, which significantly improves the system throughput via reducing the input context length, while preserving the semantic strength of cross-encoder rankers. In contrast to a standard ranking system where the context is presented to the model as pure text, we propose to use mix-interaction, a mixture of text and embedding tokens to represent the input. Specifically, MixLM encodes all items in the catalog into a few embedding tokens and stores in a nearline cache. The encoded item descriptions are used during online inference, effectively reducing the item length from a few thousand text tokens to a few embedding tokens. We share insights from deploying our MixLM framework to a real-world search application at LinkedIn, including a detailed discussion of our training pipelines, as well as a thorough analysis of our online serving infrastructure optimization. With the same latency budget and on-par relevance metrics, MixLM increased throughput by 10.0x comparing with strong baselines, 75.9x over full-text LLM rerankers. The efficiency gains delivered by MixLM enabled full-traffic deployment of LLM-powered search, which resulted in a significant 0.47\% increase in Daily Active Users (DAU) in online A/B tests.

cs.IR↗