arXiv subjects

Jiajun Cheng

Publications and source records attributed to Jiajun Cheng.

14 recordsLinked to original sources

arXiv2026

ActSWM: Action-Sensitive World Models for Long-Horizon Planning in Open-World Games

Latent world models support efficient model-predictive control by optimizing future control sequences in latent space and replanning in a receding-horizon manner. However, existing latent predictors often lack stable long-horizon rollout ability, and prediction accuracy alone does not ensure that rollouts remain responsive to the actions being planned. We identify Context Collapse, a failure mode in which autoregressive latent predictors maintain high similarity to future states while producing nearly indistinguishable futures under different action sequences. To address this issue, we propose ActSWM, an action-sensitive latent world model grounded in a transition-separation principle: a planning-useful latent dynamics model should keep alternative-action futures distinguishable and make the action associated with each local transition recoverable. Under this principle, action sensitivity is enforced as a constraint on latent rollouts rather than treated only as an auxiliary prediction target, encouraging predicted futures to preserve action-dependent differences over long horizons. Across step-drift analysis, closed-loop Minecraft planning, and cross-game local action recovery, ActSWM preserves larger action-dependent rollout gaps than existing baselines, improves task success in long-horizon interactive settings, and enables world-model-based action recovery from offline gameplay videos.

cs.RO↗

arXiv2026

LAVIFT: Latent-Action-Guided Vision Fine-Tuning for Surgical Interaction Recognition

Understanding instrument-tissue interactions is essential for context-aware surgical AI and autonomous robotic surgery. Pretrained vision-language models (VLMs) and vision encoders offer an alternative to conventional interaction classifiers by transferring broad visual and semantic knowledge. However, adapting them to fine-grained surgical interactions remains challenging: (1) freezing the vision encoder depends entirely on pretrained representations that may retain noise and provide weak spatial localization, while (2) full fine-tuning can improve global semantic alignment without ensuring that the encoder learns meaningful features in the correct action region. We address these limitations by introducing LAViFiT, an end-to-end latent-action-guided framework for vision-language fine-tuning. An inverse dynamics model captures the visual changes induced by each action, while a forward world model drives the encoder to represent action-relevant regions. A patch-level SIG Regularizer further prevents local feature collapse without additional supervision, such as bounding boxes or pseudo-labels. Experiments across multiple encoders and datasets improve recognition and image-text alignment, while representation analyses show stronger grounding over the complete instrument-tissue interaction region and more spatially coherent features.

cs.CV↗

arXiv2026

When Rules Learn: A Self-Evolving Agent for Legal Case Retrieval

Legal case retrieval remains challenging due to the complexity of legal language and the need for precise lexical alignment between queries and relevant cases. Although dense retrieval models have achieved notable progress, empirical studies show that BM25 continues to serve as a strong baseline in this domain. It motivates us to propose a self-evolving framework for rule-driven query rewriting that enhances BM25 without any parameter training. The framework equips an LLM-based agent with an automatic evaluation environment, enabling it to iteratively create rewriting rules, plan validation experiments over rule combinations, and eliminate ineffective rules based on historical feedbacks. We evaluate our method on the Chinese legal case retrieval benchmark LeCaRD-v2. Experimental results demonstrate that the proposed framework outperforms non-evolutionary baselines, including human-designed rules and greedy rule selection, particularly when powered by a highcapacity core LLM. We also conduct detailed analyses to investigate the mechanisms underlying self-evolution. Our findings reveal that LLM's capabilities to leverage previous experimental results and its intrinsic knowledge of rule elimination play critical roles in refining the rule set via self-evolution.

cs.AI↗

arXiv2026

OphIn-500K: Curating Web-Scale Visual Instructions for Scaling Ophthalmic Multimodal Large Language Models

The advancement of general medical Multimodal Large Language Models (MLLMs) has shown great potential for building conversational assistants to support clinical diagnosis. However, their adaptation to highly specialized domains such as ophthalmology remains underexplored, primarily due to the scarcity of large-scale, domain-specific instruction-tuning data. Existing ophthalmic datasets for conversational agents are often limited in scale and largely rely on images from established public benchmarks, limiting the scalability of ophthalmic MLLMs and their ability to capture real-world clinical complexity. To address this gap, we propose $\textbf{OphIn-Engine}$, an ophthalmology-specific instruction data curation pipeline that constructs high-quality instruction data from open-access ophthalmology web-scale videos. The pipeline integrates multimodal transcription for extracting image-transcript pairs, visual cue separation and scoring for identifying clinically relevant visual descriptions, and instruction synthesis with quality control for generating accurate and diverse clinical dialogues. Using this engine, we introduce $\textbf{OphIn-500K}$, a large-scale multimodal ophthalmology instruction-tuning dataset containing over 500,000 instruction instances and more than 151,000 unique images from over 29,000 video clips, formatted as visual question answering (VQA), multi-turn conversational interactions, and chain-of-thought (CoT) reasoning. Built upon this dataset, we further develop $\textbf{OphIn-VL}$, an ophthalmology-specific MLLM with advanced visual understanding and conversational capabilities. Comprehensive experiments and case studies demonstrate that OphIn-VL achieves superior performance compared with state-of-the-art general medical and domain-specific MLLMs.

cs.CV↗

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

TrajPred: Trajectory-Conditioned Joint Embedding Prediction for Surgical Instrument-Tissue Interaction Recognition in Vision-Language Models

Recognizing instruments' interactions with tissues is essential for building context-aware AI assistants in robotic surgery. Vision-language models (VLMs) have opened a new avenue for surgical perception and achieved better generalization on a wide range of tasks compared to conventional task-specific deep learning approaches. However, their performance on instrument--tissue interaction recognition remains limited, largely due to two challenges: (1) many models do not effectively leverage temporal information, and (2) alignment between vision and text often misses fine-grained action details. To address these issues, we propose TrajPred, a framework that encodes instrument trajectories to incorporate temporal motion cues and, conditioned on these trajectories, introduces a predictor module to generate visual semantic embeddings that better capture fine-grained action details. We further incorporate prompt tuning and a verb-rephrasing technique to enable smooth adaptation to the instrument--tissue interaction recognition task. Extensive experiments on the public laparoscopic benchmark, CholecT50, show that our method improves both Average Precision and Top-K accuracy. We also investigate whether visual embeddings of instrument--tissue interaction regions align better with the corresponding text by visualizing the cosine similarity between visual and textual embeddings. The visualization results indicate that the proposed method improves alignment between relevant visual and textual representations.

cs.CV↗

arXiv2026

Quality or Quantity? Error-Informed Selective Online Learning with Gaussian Processes in Multi-Agent Systems: Extended Version

Effective cooperation is pivotal in distributed learning for multi-agent systems, where the interplay between the quantity and quality of the machine learning models is crucial. This paper reveals the irrationality of indiscriminate inclusion of all models on agents for joint prediction, highlighting the imperative to prioritize quality over quantity in cooperative learning. Specifically, we present the first selective online learning framework for distributed Gaussian process (GP) regression, namely distributed error-informed GP (EIGP), that enables each agent to assess its neighboring collaborators, using the proposed selection function to choose the higher quality GP models with less prediction errors. Moreover, algorithmic enhancements are embedded within the EIGP, including a greedy algorithm (gEIGP) for accelerating prediction and an adaptive algorithm (aEIGP) for improving prediction accuracy. In addition, approaches for fast prediction and model update are introduced in conjunction with the error-informed quantification term iteration and a data deletion strategy to achieve real-time learning operations. Numerical simulations are performed to demonstrate the effectiveness of the developed methodology, showcasing its superiority over the state-of-the-art distributed GP methods with different benchmarks.

cs.LG↗

arXiv2025

PBFuzz: Agentic Directed Fuzzing for PoV Generation

Proof-of-Vulnerability (PoV) input generation is a critical task in software security and supports downstream applications such as path generation and validation. Generating a PoV input requires solving two sets of constraints: (1) reachability constraints for reaching vulnerable code locations, and (2) triggering constraints for activating the target vulnerability. Existing approaches, including directed greybox fuzzing and LLM-assisted fuzzing, struggle to efficiently satisfy these constraints. This work presents an agentic method that mimics human experts. Human analysts iteratively study code to extract semantic reachability and triggering constraints, form hypotheses about PoV triggering strategies, encode them as test inputs, and refine their understanding using debugging feedback. We automate this process with an agentic directed fuzzing framework called PBFuzz. PBFuzz tackles four challenges in agentic PoV generation: autonomous code reasoning for semantic constraint extraction, custom program-analysis tools for targeted inference, persistent memory to avoid hypothesis drift, and property-based testing for efficient constraint solving while preserving input structure. Experiments on the Magma benchmark show strong results. PBFuzz triggered 57 vulnerabilities, surpassing all baselines, and uniquely triggered 17 vulnerabilities not exposed by existing fuzzers. PBFuzz achieved this within a 30-minute budget per target, while conventional approaches use 24 hours. Median time-to-exposure was 339 seconds for PBFuzz versus 8680 seconds for AFL++ with CmpLog, giving a 25.6x efficiency improvement with an API cost of 1.83 USD per vulnerability. In real-world application, PBFuzz reproduced three FFmpeg 1-day CVEs that had no public PoVs.

cs.CR↗

arXiv2025

VAOT: Vessel-Aware Optimal Transport for Retinal Fundus Enhancement

Color fundus photography (CFP) is central to diagnosing and monitoring retinal disease, yet its acquisition variability (e.g., illumination changes) often degrades image quality, which motivates robust enhancement methods. Unpaired enhancement pipelines are typically GAN-based, however, they can distort clinically critical vasculature, altering vessel topology and endpoint integrity. Motivated by these structural alterations, we propose Vessel-Aware Optimal Transport (\textbf{VAOT}), a framework that combines an optimal-transport objective with two structure-preserving regularizers: (i) a skeleton-based loss to maintain global vascular connectivity and (ii) an endpoint-aware loss to stabilize local termini. These constraints guide learning in the unpaired setting, reducing noise while preserving vessel structure. Experimental results on synthetic degradation benchmark and downstream evaluations in vessel and lesion segmentation demonstrate the superiority of the proposed methods against several state-of-the art baselines. The code is available at https://github.com/Retinal-Research/VAOT

cs.CV↗

arXiv2025

Higher-Dimensional Moving Averages and Submanifold Genericity

We generalize results of Jones and Olsen on multi-parameter moving ergodic averages to measure-preserving actions of $\mathbb R^d$ for $d\geq 1$. In particular, we give necessary and sufficient conditions for the pointwise convergence of averages over families of boxes in $\mathbb R^d$. As an application of our characterization, we show that averages along dilates of "locally flat" submanifolds in $\mathbb R^d$ do not necessarily converge point-wise for bounded measurable functions. This is closely related to the concept of submanifold-genericity recently introduced in \cite{BFK25}.

math.DS↗

arXiv2025

SurgXBench: Explainable Vision-Language Model Benchmark for Surgery

Innovations in digital intelligence are transforming robotic surgery with more informed decision-making. Real-time awareness of surgical instrument presence and actions (e.g., cutting tissue) is essential for such systems. Yet, despite decades of research, most machine learning models for this task are trained on small datasets and still struggle to generalize. Recently, vision-Language Models (VLMs) have brought transformative advances in reasoning across visual and textual modalities. Their unprecedented generalization capabilities suggest great potential for advancing intelligent robotic surgery. However, surgical VLMs remain under-explored, and existing models show limited performance, highlighting the need for benchmark studies to assess their capabilities and limitations and to inform future development. To this end, we benchmark the zero-shot performance of several advanced VLMs on two public robotic-assisted laparoscopic datasets for instrument and action classification. Beyond standard evaluation, we integrate explainable AI to visualize VLM attention and uncover causal explanations behind their predictions. This provides a previously underexplored perspective in this field for evaluating the reliability of model predictions. We also propose several explainability analysis-based metrics to complement standard evaluations. Our analysis reveals that surgical VLMs, despite domain-specific training, often rely on weak contextual cues rather than clinically relevant visual evidence, highlighting the need for stronger visual and reasoning supervision in surgical applications.

cs.CV↗

arXiv2024

Learning Networks from Wide-Sense Stationary Stochastic Processes

Complex networked systems driven by latent inputs are common in fields like neuroscience, finance, and engineering. A key inference problem here is to learn edge connectivity from node outputs (potentials). We focus on systems governed by steady-state linear conservation laws: $X_t = {L^{\ast}}Y_{t}$, where $X_t, Y_t \in \mathbb{R}^p$ denote inputs and potentials, respectively, and the sparsity pattern of the $p \times p$ Laplacian $L^{\ast}$ encodes the edge structure. Assuming $X_t$ to be a wide-sense stationary stochastic process with a known spectral density matrix, we learn the support of $L^{\ast}$ from temporally correlated samples of $Y_t$ via an $\ell_1$-regularized Whittle's maximum likelihood estimator (MLE). The regularization is particularly useful for learning large-scale networks in the high-dimensional setting where the network size $p$ significantly exceeds the number of samples $n$. We show that the MLE problem is strictly convex, admitting a unique solution. Under a novel mutual incoherence condition and certain sufficient conditions on $(n, p, d)$, we show that the ML estimate recovers the sparsity pattern of $L^\ast$ with high probability, where $d$ is the maximum degree of the graph underlying $L^{\ast}$. We provide recovery guarantees for $L^\ast$ in element-wise maximum, Frobenius, and operator norms. Finally, we complement our theoretical results with several simulation studies on synthetic and benchmark datasets, including engineered systems (power and water networks), and real-world datasets from neural systems (such as the human brain).

stat.ML↗

arXiv2023

Differential Analysis for Networks Obeying Conservation Laws

Networked systems that occur in various domains, such as the power grid, the brain, and opinion networks, are known to obey conservation laws. For instance, electric networks obey Kirchoff's laws, and social networks display opinion consensus. Such conservation laws are often modeled as balance equations that relate appropriate injected flows and potentials at the nodes of the networks. A recent line of work considers the problem of estimating the unknown structure of such networked systems from observations of node potentials (and only the knowledge of the statistics of injected flows). Given the dynamic nature of the systems under consideration, an equally important task is estimating the change in the structure of the network from data -- the so called differential network analysis problem. That is, given two sets of node potential observations, the goal is to estimate the structural differences between the underlying networks. We formulate this novel differential network analysis problem for systems obeying conservation laws and devise a convex estimator to learn the edge changes directly from node potentials. We derive conditions under which the estimate is unique in the high-dimensional regime and devise an efficient ADMM-based approach to perform the estimation. Finally, we demonstrate the performance of our approach on synthetic and benchmark power network data.

eess.SY↗

arXiv2022

Specular: Towards Secure, Trust-minimized Optimistic Blockchain Execution

An optimistic rollup (ORU) scales a blockchain's throughput by delegating computation to an untrusted remote chain (L2), refereeing any state claim disagreements between mutually distrusting L2 operators via an interactive dispute resolution protocol. State-of-the-art ORUs employ a monolithic dispute resolution protocol that tightly couples an L1 referee with a specific L2 client binary--oblivious to the system's higher-level semantics. We argue that this approach (1) magnifies monoculture failure risk, by precluding trust-minimized and permissionless participation using operator-chosen client software; (2) leads to an unnecessarily large and difficult-to-audit TCB; and, (3) suffers from a frequently-triggered, yet opaque upgrade process--both further increasing auditing overhead, and broadening the governance attack surface. To address these concerns, we outline a methodology for designing a secure and resilient ORU with a minimal TCB, by facilitating opportunistic 1-of-N-version programming. Due to its unique challenges and opportunities, we ground this work concretely in the context of the Ethereum ecosystem--where ORUs have gained significant traction. Specifically, we design a semantically-aware proof system, natively targeting the EVM and its instruction set. We present an implementation in a new ORU, Specular, that opportunistically leverages Ethereum's existing client diversity with minimal source modification, demonstrating our approach's feasibility.

cs.CR↗