Peer Revenue Fully funded

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science

Monday 24 August

Information Retrieval

WARP: Wasserstein-Aligned RAG for Population Opinions

Aman Singh Thakur, Aditya Agrawal, Alwarappan Nakkiran et al. (+1 more)

RAG systems are increasingly used to summarize what large collections of documents say. A user asks "What do people think about X?" and receives an answer that reads as consensus. But standard top-k retrieval ranks documents by query similarity, not by how faithfully they represent the population, so minority views quietly disappear. Existing fixes fall short. Diversity re-rankers like MMR and DPP spread retrieved documents apart, but with no target distribution to aim for. Calibration methods based on KL or JS divergence do target one, yet treat opinion bins as unordered: confusing strong positive with strong negative costs no more than an adjacent-bin miss. We introduce WARP, a family of post-retrieval algorithms that calibrate retrieved evidence to the population's opinion distribution. WARP first recovers underrepresented opinions that cosine ranking may bury, then uses Wasserstein-1 distance to select documents whose sentiment-intensity distribution matches the population target, capturing the ordinal structure ignored by KL and JS divergence. We develop three variants for dense, sparse, and variable candidate pools, trading off calibration quality and speed. Across three review domains spanning 35K documents, 156 queries, and 26 entities, WARP's domain-matched variants reduce distributional error by at least 43% with sub-second latency. These gains carry through to generation: a five-judge LLM panel prefers WARP-generated answers in 86% of decided comparisons at k <= 5.
Read the full abstract

All authors Aman Singh Thakur, Aditya Agrawal, Alwarappan Nakkiran, Alex Karlsson

Machine Learning

Mapping the Concept Landscape: Structural Perception of Global Distributions for Transparent Data Pruning

Dongyue Wu and Tao Ma

Existing data pruning methods predominantly rely on high-dimensional feature embeddings to measure sample importance. However, these compressed vectors often obscure fine-grained semantic interactions, leading to suboptimal coverage of rare semantic concepts in the pruned subsets. In this paper, we propose Mapping the Concept Landscape (MCL), a novel structural perception framework for transparent data pruning. Instead of abstract embeddings, we represent each image-caption pair as an explicit sample-level graph comprising entities, events, and attributes. By integrating these individual graphs into a comprehensive dataset-level graph, we characterize the global distribution of semantic concepts and quantify their rarity across the entire corpus. Based on this structured perception, we develop a greedy concept-coverage maximization algorithm that iteratively selects samples to maximize the marginal gain of high-value, under-represented concepts. Experimental results on various benchmarks demonstrate that our method not only achieves superior pruning efficiency compared to state-of-the-art methods but also provides a transparent and interpretable audit trail for the selection process.
Read the full abstract

Computation and Language

SAVER: Selective Auditing of Verbal Evidence for Error Recovery in VLM Change Reasoning

Youdi Li

Vision-language models (VLMs) frequently fail at visual change reasoning, even when their vision encoders contain sufficient information. We observe that correct VLM outputs tend to contain explicit verbal evidence (object names, colors, spatial locations) that supports the claimed change, while incorrect outputs often lack such evidence. We propose SAVER (Selective Auditing of Verbal Evidence for Error Recovery), a lightweight, rule-based method that parses VLM responses for this evidence and triggers structured reprompting only when evidence is missing or inconsistent. Across three change detection benchmarks and four VLMs, SAVER significantly improves accuracy on tasks where errors stem from the model failing to articulate what it saw (expression failures), with gains up to +25.8% on CLEVR-Change. The evidence patterns can also be generated by an LLM in a single call, matching the hand-tuned gate on CLEVR-Change. Ablation experiments confirm that the evidence gate, not reprompting alone, drives the improvement.
Read the full abstract

Information Retrieval

Same Agent, Different Answers: A Repeat-Aware Audit of Corpus-Induced Answer Churn in Retrieval-Augmented QA

Jingjie Ning and Xueqi Li

A retrieval-augmented QA system can return different answers after an index expansion even when its requested model identifier, prompt, retrieval policy, evidence depth, rendering, and exposed generation controls are held fixed. Aggregate accuracy may hide these changes when gains and losses cancel, while ordinary generation variability makes one-shot comparisons overstate update effects. We call the hidden phenomenon accuracy-blind answer churn and introduce the Snapshot Compatibility Audit, which estimates excess answer churn by subtracting same-snapshot repeat disagreement from cross-snapshot disagreement. We instantiate it by expanding one frozen FineWeb prefix from one to seven shards. In a preregistered 400-question Natural Questions study, normalized-exact and blinded-semantic excess churn are 6.44 and 10.25 percentage points while exact-match accuracy changes by only $-1.50$ points. A post-hoc analysis finds repeat-stable semantic flips on 40/400 questions. A separately preregistered 200-question TriviaQA study yields smaller, directionally consistent excess churn while exact-match accuracy moves in the opposite direction. An outcome-blind post-hoc 100-question subset replication with a second DeepSeek generator and serving configuration finds 8.75 pp of semantic excess churn even as exact match rises by 3.00 percentage points. Answer-level compatibility can therefore fail without a conspicuous or consistently directed utility shift. Retrieval-augmented releases should audit compatibility alongside utility.
Read the full abstract

Machine Learning

Thinking at the Right Size: Amortized Distillation Across Post-Trained LLMs

Yan Zhou, Sara Kangaslahti, Jonathan Geuter et al. (+4 more)

Practical deployment of large language models (LLMs) requires families of post-trained variants—instruction-tuned, reasoning-tuned, and chat-style models—each at multiple sizes to meet diverse latency and memory budgets. Producing each (variant, size) pair independently is prohibitive, so model families typically span only a handful of coarse-grained sizes per post-trained variant. Boomerang distillation (Kangaslahti et al., 2026) reduces this cost along the size axis for base models. Through model size interpolation, it constructs models of intermediate sizes from a single teacher-student pair without additional training. However, it still treats each post-trained variant as a separate object of optimization. We introduce ADAPT—Amortized Distillation Across Post-Trained LLMs—a framework for amortizing distillation across both axes of a model family: size and post-training variant, producing $L \times K$ models for $L$ interpolated sizes across $K$ post-trained variants with a single distillation run. ADAPT combines two components. First, a two-phase distillation procedure constructs post-trained students through pre-training alignment and supervised fine-tuning distillation, enabling smooth size–performance interpolation on generation and reasoning tasks. Second, weight-delta initialization approximates this construction across post-trained variants by transferring the distillation-induced weight change from the base model to students initialized from different post-trained variants. The resulting continuum of interpolated models also enables adaptive model-size selection at inference time, improving the compute–accuracy trade-off for long-form reasoning tasks.
Read the full abstract

All authors Yan Zhou, Sara Kangaslahti, Jonathan Geuter, Nihal V. Nayak, Marco Fumero, Francesco Locatello, David Alvarez-Melis

Databases

Why We Created Yet Another Memory Framework: Understanding MGA's Role in Next-Gen Database Systems

Vikramraj Sitpal, Pei Li, Shubham Kumar et al. (+3 more)

Despite the presence of multiple memory regions in modern database systems, supporting an efficient form of memory remains a challenge under production constraints. In enterprise-grade data systems, existing abstractions impose a trade-off between coarse-grained global sharing and strict process isolation, resulting in data copying, memory fragmentation, and limited support for controlled sharing. These challenges become more pronounced as workloads grow more diverse, and systems must tolerate process failures while maintaining predictable performance. This paper introduces the Managed Global Area (MGA), a scoped shared-memory abstraction in Oracle AI Database that addresses these limitations. MGA allows components to explicitly define allocation source, membership, and coordination semantics across selected processes while integrating with a production database engine. Unlike fully shared memory regions in Oracle, such as the System Global Area (SGA), MGA supports dynamic process membership and modular memory usage without imposing system-wide visibility. We evaluate MGA on analytical and AI workloads that stress shared-memory execution, including TPC-H hash joins and ONNX Runtime inference. Under concurrent execution, MGA reduces latency for join-intensive TPC-H queries by up to 35%. For ONNX- based inference, MGA-enabled model sharing reduces memory footprint by up to 90% and lowers large-model inference latency by up to 37%. These results demonstrate that dynamically scoped shared memory can improve both efficiency and predictability in production database systems.
Read the full abstract

All authors Vikramraj Sitpal, Pei Li, Shubham Kumar, Somansh Reddy Satish, Ravi Thammaiah, Nagarajan Muthukrishnan

Artificial Intelligence

Your AI, On a Dial: Controlling Investment Bias in LLMs with a Single Neuron

Sahong Park, Suhwan Park, Hoyoung Lee et al. (+8 more)

Large language models (LLMs) are increasingly used in investment decision-making, yet prior work shows that they exhibit systematic, model-specific investment preferences. We study whether a model's overall investment stance can be calibrated to a specified direction and strength. We introduce an investment-bias dial, an inference-time intervention on a single neuron that continuously adjusts a model-level decision prior—its overall tendency toward buying or selling—without targeting specific firms or investment attributes. Using matched positive and negative evidence, we evaluate five open-weight LLMs and find that the dial produces monotonic changes in investment stance without modifying prompts or model parameters. At the response level, the dial shifts both investment decisions and the evidential emphasis of generated rationales under identical inputs. In an agentic retrieval setting, the dial also changes what information the model searches for, which evidence it selects, and which evidence is reflected in its final analysis. In a long-context evaluation, the dial maintains stable stance control as context length increases, whereas a matched system-prompt instruction progressively attenuates. We further show that changes in the dial propagate to security rankings and downstream portfolio composition in an exploratory backtest. Overall, our results show that an LLM's aggregate investment stance can be calibrated toward a specified target at inference time.
Read the full abstract

All authors Sahong Park, Suhwan Park, Hoyoung Lee, Gakyung Kwon, Wonbin Ahn, Jaewon Choi, Alejandro Lopez-Lira, Yoon Kim, Chanyeol Choi, Hyeongwoo Kong, Yongjae Lee

Machine Learning

RIBOSPAN: A Long-Context RNA Foundation Model for Versatile RNA Modeling

Ziyuan Wang, Bohao Tang, Fei Zhang et al. (+2 more)

Full-length RNAs, particularly messenger RNAs, often exceed the context lengths used to pretrain existing RNA foundation models, limiting complete-transcript modeling at single-nucleotide resolution. We present RIBOSPAN, a 1.61-billion-parameter bidirectional RNA foundation model natively pretrained with context lengths up to 10,240 nt. RIBOSPAN combines dense bidirectional self-attention, single-nucleotide tokenization, and attention-isolated sequence packing to enable high-resolution modeling of complete long RNAs. Native 10K pretraining preserves strong reconstruction at 10,240 tokens and, in a controlled long-context benchmark, maintains strong contextual responsiveness and context-specific representation separation while keeping perturbation-induced changes highly localized. Inference-time YaRN scaling recovers much of the contextual organization lost by direct short-context extrapolation, but induces substantially greater distal representation diffusion. Frozen RNA-type evaluations show that RIBOSPAN learns state-of-the-art RNA representations, with a particularly clear advantage on long RNAs. Across downstream biological benchmarks, RIBOSPAN emerges as the strongest encoder-only RNA foundation model, achieving state-of-the-art performance in both full-transcript biological property prediction and zero-shot mutation-fitness modeling. Building on the same backbone, we develop a multidimensionally conditioned discrete-diffusion framework for full-length mRNA generation and redesign, including synonymous-codon diffusion for protein-preserving CDS optimization. Together, RIBOSPAN establishes a powerful long-context foundation for transferable RNA representation learning, biological prediction, and full-transcript mRNA design.
Read the full abstract

All authors Ziyuan Wang, Bohao Tang, Fei Zhang, Shuo Han, Pengfei Liu

Artificial Intelligence

GSAR: Goal-State-Anchor Rewards for Mobile GUI Agents with Self-Evolving Data Synthesis

Long Zhang, Yuhan Chen, Chaoran Zhang et al. (+7 more)

Vision-Language Models (VLMs) based GUI agents stand to benefit significantly from online reinforcement learning (RL). However, their training is bottlenecked by two fundamental issues: current data synthesis methods for GUI Agents rely on specific environments and struggle to generate diverse data, while existing evaluators either suffer from limited scalability or provide inaccurate and unreliable reward signals. To overcome these challenges, we introduce GSAR (Goal-State-Anchor Reward), a RL reward framework that supports scalable task generation and delivers reliable reward signals for stable and efficient policy optimization. Our approach features self-evolving data synthesis, which produces multiple environments through task execution and generates diverse tasks and goal states. Complementing this, a state-anchor mechanism automatically annotates task-relevant UI elements in successful goal states as reference anchors. During RL training, these reference anchors provide accurate, scalable reward signals that substantially enhance efficiency. Extensive evaluations demonstrate that our framework achieves over 90% accuracy on offline trajectory verification and performs closest to rule-based methods. Furthermore, agents trained using our reward framework exhibit strong performance on both AndroidWorld and our constructed benchmark, establishing a scalable approach for GUI agent training.
Read the full abstract

All authors Long Zhang, Yuhan Chen, Chaoran Zhang, Wanxia Cao, Kun Huang, Pengzhi Gao, Wei Liu, Jian Luan, Chenliang Li, Lixin Zou

Artificial Intelligence

FinixDoc: Rethinking Financial Document Parsing Beyond Saturated Benchmarks

Hang Wang, Jin Zhang, Guoliang Xu et al. (+13 more)

Financial document parsing requires accuracy, structural consistency, and verifiability that current benchmarks often fail to reflect. We present FinixDoc, an end-to-end agentic parsing system for real-world financial documents, with FinixDoc-VL, a 4B-scale vision-language model built on Qwen3-VL-4B, as its core parser. To characterize the gap between benchmark and deployment performance, we introduce a Document Parsing Capability Matrix organized along two practical axes: visual quality and document scale. Guided by this matrix, FinixDoc-VL is trained with a domain-adapted recipe combining homoglyph-aware contrastive learning and multi-stage reinforcement learning with composite domain-specific rewards. To better leverage our accumulated advantage in low-quality financial-document data and support large-scale, high-quality data production, we further build a human-in-the-loop Data Factory pipeline with confidence-aware expert review. For evaluation, we construct FinixDocBench, a financial-domain evaluation suite covering digital-native, camera-captured, ultra-large-page, and internal-workflow scenarios, with a compliance-reviewed subset released alongside this technical report. On its main subsets, FinixDoc-VL achieves the highest overall score (81.43) among evaluated baselines, outperforming the next-best open-source model by 5.13 points, with the largest gains on internal financial workflows (FinixInner: 84.08 vs. 78.73).
Read the full abstract

All authors Hang Wang, Jin Zhang, Guoliang Xu, Pengyue Lu, Yao Li, Zijiao Zhang, Tianyu Huang, Weiqi Xiong, Yulong Wang, Chuqiao Lu, Wenkang Huang, Kai Yang, Yadong Li, Hui Li, Xingzhong Xu, Xiao Xu

Game Theory

Equilibrium in Multi-Agent Reinforcement Learning

Maurizio D'Andrea and Bar Light

Standard solution concepts for stochastic games, such as Markov perfect equilibrium and Markov coarse correlated equilibrium, are computationally difficult, and thus, standard decentralized reinforcement-learning algorithms should not generally be expected to converge to them. In this paper, we study the equilibrium generated by such algorithms. In particular, we introduce a new solution concept for stochastic games, Markov Bayes coarse correlated equilibrium (MBCCE), defined as a distribution over states and stationary policy profiles such that, after observing the state but before observing her recommended action, no player can gain by choosing a different current action, with the sampled policy profile governing play thereafter. We discuss the parallels between MBCCE and coarse correlated equilibrium (CCE) in finite normal-form games and show that MBCCE retains several of its key properties. We then introduce a corresponding regret notion, adaptive Markov coarse regret (AMCR), and show that vanishing AMCR implies that every accumulation point of the empirical distribution of realized states and policy profiles is an MBCCE. Crucially, we show that achieving AMCR reduces to two standard learning tasks: minimizing external regret at each state and accurately evaluating the current joint policy. We then prove that under mild conditions these properties hold for two natural RL algorithmic designs: a decentralized asynchronous actor–critic algorithm through a new two-timescale stochastic-approximation analysis, and a standard episodic multi-agent projected policy-gradient method. Hence, both algorithms generate approximate MBCCEs, and we establish explicit finite-time convergence rates for both.
Read the full abstract

Machine Learning

Hierarchy-Aware Supervised Uncertainty Estimation for Black-box LLM Taxonomic Reasoning

Shuting Xie, Nathaniel Lesperance and Graham W. Taylor

Large language models (LLMs) are increasingly used for scientific decision support, yet reliable confidence estimation remains difficult in black-box settings. We study uncertainty estimation for hierarchical taxonomic reasoning generated by a black-box LLM in a long-tailed biodiversity monitoring pipeline. Using proxy features extracted by an open-source tool LLM, we train lightweight supervised estimators with hierarchy-aware supervision to predict rank-wise correctness. Across three tool LLMs, the supervised estimators consistently outperform a token-likelihood baseline for micro discrimination and selective prediction under a single global rejection threshold, improving micro AUROC from 0.57 to 0.75–0.80. The best results are achieved by a rank-specific multi-head design (H3), suggesting that accounting for hierarchical output structure is important when a unified abstention rule is required. Our code is publicly available at https://github.com/uoguelph-mlrg/hierarchy-aware-llm-uq
Read the full abstract

Information Theory

Entropy of Bernoulli Measures Conditioned on Affine Subspaces and a Problem of Ancheta–Massey

Yihong Wu

A textbook result in information theory is that linear encoders achieve the entropy for lossless compression of Bernoulli source with parameter $p$. For lossy compression, however, linearity is known to incur strict suboptimality compared to the rate-distortion function. Massey asked whether the optimal rate for linear encoding is achieved simply by compressing a fraction of the bits linearly and losslessly and estimating the rest by zero \cite{Massey1978}. For $p=\frac12$, Ancheta answered this question affirmatively \cite{Ancheta1978}. This note extends Ancheta's result to all $p<\frac12$. The key argument is to bound the entropy of the posterior distribution conditioned on an affine subspace in terms of its marginals. The proof was discovered by GPT-5.6 Sol in an interactive process guided by the author. The purpose of the present note is to communicate a simplified version of this proof and to make connections with the existing literature on coding theory and spin glass theory.
Read the full abstract

Machine Learning · Cross-listed from math.OC

Mirror descent algorithms with logarithmic barriers

Alberto De Marchi, Yura Malitsky and Adrien B. Taylor

We derive convergence guarantees for mirror descent and proximal mirror descent with a logarithmic barrier as the distance-generating function. When the solution lies on the boundary, the Bregman divergence blows up and classical guarantees become vacuous. While existing remedies recover $O(\log k/k)$ rates by adapting classical bounds, we propose a more direct route in which the Bregman distance to the solution never appears, and which achieves the same rate with constant stepsize. We also construct an example showing that this rate cannot be improved in general. Finally, we compare the proposed approach with interior-point methods.
Read the full abstract

Multiagent Systems

Minimal Local Simulation Foundations for LLM- and VLM-Driven Agents in 2D and 3D Environments

Ryuki Hyodo

Large language models (LLMs) and vision-language models (VLMs) are expanding the range of behaviors that can be represented in agent-based simulations, but many contemporary platforms are difficult to study, modify, or run on ordinary computers. We present two intentionally minimal simulation foundations for education and rapid prototyping. SD-AgentFoundry-2D provides a two-dimensional multi-agent environment in which locally hosted LLM agents move, communicate, respond to place occupancy, and encounter spatially localized fire events. SD-AgentFoundry-3D provides a three-dimensional digital-twin environment in which a locally hosted VLM receives first-person images and produces natural-language movement instructions. Both codebases are designed to run locally on macOS, Windows, and Linux and are deliberately left open to modification rather than developed as finished applications. Together, they offer accessible starting points for learning about generative social simulation and for building domain-specific extensions.
Read the full abstract

Artificial Intelligence

Let the Bullets Fly: Multimodal Fake News Detection with Temporal-Aligned Generative Danmaku

Xiansheng Luo, Chaowei Zhang, Zewei Zhang et al. (+2 more)

The social interactions among crowds via Danmaku (a.k.a., bullet comments) on modern multimedia platforms can facilitate both viewpoint conflicts and consensus, providing fine-grained discriminative social signals that can benefit fake news detection. However, the inherent accumulation latency of Danmaku in real-world scenarios violates the real-time necessity of fake news detection, making the studies of Danmaku-related fake news detection underexplored. To break this violation, we simulate this temporal-aware user interactive process by proposing a novel temporal Generative danmaku framework, called Genda, which consists of: (1) a Danmaku Trigger for predicting the timing and intensity of user reactions; and (2) a Danmaku Generator for synthesizing corresponding semantic and emotional expressions, thereby mutually constructing a temporally aligned and human-like pseudo Danmaku streams. To make the generated Danmaku useful for identifying fake news videos, we further design a Danmaku-guided Temporal Multimodal fake news detection model - DM-FEND, which enables fine-grained multimodal interactions among video, audio, text, and Danmaku, enhancing dynamic modalities alignment and semantic noise inhibition. The experimental results demonstrate that DM-FEND consistently outperforms state-of-the-art baselines across both Chinese (FakeSV) and English (FakeTT) benchmarks. Further ablations validate the crucial role of temporal Danmaku modeling in enhancing robustness and discriminative capability. Finally, this study offers a bright and robust solution for multimodal fake news detection in modern social interactive fashions by bridging the temporal inconsistency between news and user behaviors.
Read the full abstract

All authors Xiansheng Luo, Chaowei Zhang, Zewei Zhang, Yi Zhu, Jipeng Qiang

Artificial Intelligence

Beyond the Harness: End-to-End Optimization of Context Artifacts for Enterprise Text-to-SQL

Kate Gwimm and Carson Eisenach

Deploying LLMs for enterprise Text-to-SQL is bottlenecked less by the model than by what context reaches it: business logic spans thousands of tables, and no model can ingest a full catalog at once. We argue that the most effective place to intervene is therefore the knowledge-base context the model consumes, and that this context should be constructed from historical usage rather than tuned for as a fixed input. Using a query-DAG decomposition–the same family of intermediates that enterprise benchmarks like BEAVER annotate, here recovered from production SQL–we compare the value of oracle query graphs versus retrieved knowledge-base context. In this ablation, retrieved knowledge-base context provides the largest marginal improvement when added to the full oracle graph. Building on this, we optimize a distillation procedure that turns historical query profiles into reusable SQL reference cards. On a benchmark of 5176 production queries from a major online retailer, optimizing these context artifacts yields larger gains (${\sim}12$–$25\%$ AST similarity) than optimizing the retrieval harness (${\sim}3$–$12\%$). On the public BEAVER benchmark, which lacks the production-usage signals available in our internal setting, the picture is more mixed: table cards alone perform about the same as raw historical SQL. The best optimized variant retrieves both cards and raw SQL, scoring $9.00\%$ versus $6.33\%$ (p-value $0.12$) for the comparable baseline on a held-out $N{=}300$ subset, using retrieved context and harness changes but no agentic loop.
Read the full abstract

Numerical Analysis · Cross-listed from math.RA

Sign Propagation of Principal Minors in Fully Semimonotone Matrices and Stone's Conjecture

Sajal Ghosh

Stone conjectured in 1981 that every fully semimonotone $\mathbf{Q}_0$-matrix is a $\mathbf{P}_0$-matrix; Murthy and Parthasarathy (1995) proved this for orders up to $4$ and for several special classes. We study the principal minors of fully semimonotone matrices $A\in\Ezerof$ without using $\Qzero$. Let $\G(A)$ be the graph whose vertices are the index sets $\alpha$ with $\det A_{\alpha\alpha}\neq 0$ (including $\alpha=\emptyset$), two vertices being adjacent when they differ in exactly one index. We prove that the sign of the principal minor is constant on every connected component of $\G(A)$, and positive on the component of $\emptyset$. Consequences: an $\Ezerof$-matrix with no vanishing principal minor is a $\mathbf{P}$-matrix, and any $\Ezerof$-matrix satisfying a simple “descending” condition on its nonvanishing minors is a $\mathbf{P}_0$-matrix. We show that a sign change across two steps through vanishing minors forces strictly positive coupling in the corresponding principal pivotal transform, and that a principal submatrix of minimal order with negative determinant is an almost-$\mathbf{P}_0$ matrix whose inverse lies in $\Ezerof\cap\Nzero$ and has zero diagonal. Explicit examples show that the component structure can contain negative components, that $\det A>0$ does not force $A\in\Pzero$ in $\Ezerof$, that $\Ezerof$ is not invariant under $A\mapsto A+\varepsilon I$, and that $\Ezerof\cap\Pzero$ contains matrices with $\det A>0$ outside $\Qzero$. Stone's conjecture itself remains open.
Read the full abstract

Computer Vision

VeCAS: Vessel-Focused Contrast-Free Angiogram Synthesis for Vascular Interventions

De-Xing Huang, Chen-Yu Wang, Hao Liang et al. (+10 more)

X-ray angiography relies on iodinated contrast agents to visualize vascular structures during image-guided interventions. However, contrast administration carries risks of adverse events, motivating the development of contrast-free alternatives. Generating X-ray angiograms directly from non-contrast X-ray images offers a potential solution, but existing approaches remain limited by (i) insufficient control over vascular localization and (ii) inefficient modeling of redundant background content. To address these challenges, we propose VeCAS, a two-stage vessel-focused contrast-free angiogram synthesis framework that separates vascular structure localization from angiographic appearance synthesis. In Stage I, a discriminative model localizes vascular structures in non-contrast X-ray images, while cross-modality latent distillation transfers vessel-sensitive knowledge from X-ray angiograms during training. In Stage II, a vessel-focused inpainting model synthesizes angiographic appearance within the localized vascular regions while preserving the non-vascular background. Experiments on an in-house lower-limb vascular intervention dataset show that VeCAS outperforms the comparison methods in terms of vascular structural fidelity and image quality. Visual Turing tests and physician assessments indicate the perceptual realism of the synthesized angiograms. In addition, robotic guidewire navigation experiments in vascular phantoms show that VeCAS guidance reduces the time to target by 41.4% and the number of operation steps by 40.7% compared with non-contrast guidance. Together, these results suggest the potential of VeCAS to serve as “meta contrast agent” for vascular interventions.
Read the full abstract

All authors De-Xing Huang, Chen-Yu Wang, Hao Liang, Xiao-Hu Zhou, Mei-Jiang Gui, Tian-Yu Xiang, Qin-Yi Zhang, Chen Wang, Xiao-Liang Xie, Shi-Qi Liu, Ming-Yuan Liu, Zhen-Chang Wang, Zeng-Guang Hou

Machine Learning

DIME: Query-Efficient Framework for Membership Inference on Diffusion Models

Tue Do and Daniel Alabi

Membership inference attacks expose whether individual records were used to train a model, yet existing attacks on diffusion models are largely heuristic and can require substantial query budgets. We introduce DIME (Denoiser Ideal Membership Error), a theoretically grounded and query-efficient framework for membership inference on diffusion models. Our starting point is an exact characterization of the optimal diffusion denoiser for a finite training set, which reveals that membership leakage is governed by the denoiser's implicit reconstruction error. This error decomposes into two complementary signals: a bias term, capturing reconstruction accuracy, and a previously unexplored local crowding term, capturing the geometry of nearby training examples. Both admit efficient estimators using only model queries, yielding a practical attack with as few as two queries. Across CIFAR-10/100, STL10-U, CelebA, and ImageNet, DIME consistently outperforms prior attacks at comparable or substantially lower query cost, improving TPR at 1% FPR by up to $3\times$; remarkably, its two-query variant can outperform existing 30-query baselines. Finally, we suggest, discuss, and evaluate specific defenses to counteract such powerful membership tests.
Read the full abstract

Computer Vision

SiZeUp: Fast 3D Proxy from Aerial Images via Depth Ordinal Loss

Wenjun Zhou, Yunshan Li, Qiaoyu Zhu et al. (+4 more)

We present SiZeUp, a fast and scalable approach for constructing large-scale 3D urban proxy models directly from calibrated oblique aerial imagery. Our method adopts a height-from-footprint representation, reducing 3D building abstraction to a low-dimensional optimization problem in which building footprints are extruded by a single height parameter. To enable efficient and robust height estimation, we introduce an ordinal depth consistency loss that enforces agreement between the relative depth ordering of rendered proxies and depth priors predicted by a monocular depth model. This is realized through a differentiable renderer that maps parametric building proxies into multi-view depth images, allowing gradients to be propagated from depth supervision to building heights. Our ordinal formulation produces stable optimization in practice and avoids explicit feature matching or dense point cloud reconstruction. Rather than relying on metric depth, which can be unreliable under monocular scale ambiguity, our ordinal depth consistency loss operates on relative depths, providing a more reliable signal across views. Combined with an efficient dynamic view selection, our approach achieves a 23-52$\times$ speedup over state-of-the-art proxy reconstruction pipelines while maintaining comparable proxy-level coverage and volume consistency, making it well suited for large-scale urban modeling tasks.
Read the full abstract

All authors Wenjun Zhou, Yunshan Li, Qiaoyu Zhu, Weidan Xiong, Hao Zhang, Daniel Cohen-Or, Hui Huang

Machine Learning

Fairness-Aware Mixture-of-Experts via Subgroup Reweighting and Gate Regularization

Sunhee Hwang

Deep learning models often produce performance disparities across demographic groups, due to the training data imbalance with respect to sensitive attributes such as gender or age. To address this problem, existing work has explored fair representation learning, data re-sampling, and adversarial training, which can be broadly categorized into two main approaches. Single-stage methods typically learn a shared representation for fairness, but often struggle to handle heterogeneous subgroup distributions. Two-stage methods learn representations separately from the final prediction task, which can lead to misalignment between fairness objectives and downstream predictions. We identify routing-induced bias, a failure mode in which subgroup imbalance drives the gating network to route subgroups onto a few experts, and propose an end-to-end Mixture-of-Experts (MoE) framework that corrects it. Specifically, we apply subgroup reweighting to correct data imbalance, and introduce gate entropy regularization to prevent routing from collapsing onto subgroup attributes, keeping expert utilization both balanced and interpretable. Beyond improving fairness, the routing distribution offers an interpretable view of how subgroups are allocated across experts. Experimental results demonstrate that the proposed approach improves fairness while maintaining competitive predictive performance.
Read the full abstract

Computer Vision

Direct, Parallel, or Sequential? A Comparative Study of Training-Free Multi-Subject Image-to-Video Generation

Yanliang Qi, Kexi Chen, Muchao Ye et al. (+1 more)

Text-conditioned image-to-video (I2V) generation has advanced rapidly, yet generating videos with multiple subjects remains challenging. A model must simultaneously preserve the appearance of each subject, assign distinct motions, and maintain coherent spatial and temporal interactions. This paper presents a systematic study of three representative paradigms for training-free multi-subject I2V generation: direct, parallel, and sequential generation. Direct generation applies a pretrained I2V model to the complete reference image and prompt, requiring all subjects and motions to be synthesized jointly. Parallel and sequential generation instead decompose the reference image and prompt into subject-specific visual and textual conditions. Parallel generation synthesizes each subject independently and subsequently composes the resulting videos, reducing the complexity of each generation step at the cost of weaker inter-subject context. Sequential generation first synthesizes a background video and then progressively introduces individual subjects. This preserves accumulated scene context but introduces sensitivity to subject ordering and error propagation. We empirically evaluate the three paradigms across diverse multi-subject scenes, comparing appearance preservation, motion fidelity, temporal consistency, and inter-subject coherence, while also characterizing their distinct failure modes. Our findings reveal the strengths and limitations of each paradigm and offer practical insights for designing controllable multi-subject video generation systems.
Read the full abstract

All authors Yanliang Qi, Kexi Chen, Muchao Ye, Haomiao Ni

Computation and Language

Industrial-Instruction: An End-to-End Framework for Building Instruction-Tuning and Benchmark Datasets from Industrial Technical Reports

Parsa Bakhtiari, Hassan Bashiri, Alireza Khalilipour et al. (+2 more)

Industrial technical reports contain high-value knowledge for maintenance, troubleshooting, and product engineering, but their heterogeneous structure (dense prose, specifications, tables) makes them difficult to index and reason over with standard retrieval and QA pipelines, and no public instruction-tuning or benchmark datasets are built from such documents. We address this gap with Industrial-Instruction, contributing (i) two open QA datasets built from real industrial technical reports and (ii) the end-to-end pipeline that produces them. Using 906 public Panasonic documents (7,525 pages), we apply layout-aware extraction, build a semantic retrieval index, and synthesize multiple-choice QA grounded in retrieved evidence under five query-document relationships (irrelevant retrieval, single-/multi-document support, single-/multi-document answer). After filtering an initial 23.9k generated samples, each dataset provides approximately 13.6k QA pairs with source documents and a held-out benchmark split. Fine-tuning small open LLMs (under 10B parameters) improves Set-Match Accuracy from 28.5% to 42.0% and F1 from 46.6% to 63.5% on the Panasonic benchmark. We release two parallel versions built by the same pipeline: one generated with the open-weight Qwen3-30B-A3B-Instruct model and one with the closed, API-based Claude-Opus-4.6 model, enabling a direct comparison of open- versus frontier-model data generation. The Claude-Opus-4.6 dataset yields a cleaner raw corpus and larger fine-tuning gains, at roughly two orders of magnitude higher cost. MMLU evaluation shows models trained on the Claude-Opus-4.6 data retain essentially all general knowledge, versus a small but measurable forgetting effect for the Qwen-generated data. Together, these datasets and pipeline offer a practical, reproducible path toward scalable industrial benchmarks and training data from real-world documentation.
Read the full abstract

All authors Parsa Bakhtiari, Hassan Bashiri, Alireza Khalilipour, Masoud Nasiripour, Moharram Challenger

Networking

The Surprising Effectiveness of LLMs in BGP Security: Mining An Unprecedented Amount of Incidents and Boosting Anomaly Detection

Libin Liu, Wenzhou Yang, Li Chen et al. (+2 more)

Border Gateway Protocol (BGP) security is critical to Internet infrastructure, yet progress in routing anomaly detection has been limited by the scarcity of publicly available incident datasets, which contain only 18 recorded cases. We observe that public operator mailing lists, e.g., NANOG and AusNOG, contain abundant yet largely untapped reports of real-world routing anomalies. To leverage this source, we develop an LLM-assisted extraction pipeline that identifies 244 candidate incidents from historical discussion threads. After expert validation, we curate a verified benchmark containing 232 confirmed routing anomaly events, making it 11.89X larger than existing dataset. Using this benchmark, we show that existing routing anomaly detection systems generalize poorly to diverse real-world incidents. At the same time, we find that some general-purpose LLMs without routing-specific adaptation can identify a subset of routing anomalies, but their performance varies across models and remains insufficient for reliable routing anomaly detection. Motivated by this observation, we design ROUTELLM, an LLM-based routing anomaly detector that integrates BGP-semantic-aware tokenization, routing-domain adaptation, and time-aware routing evidence retrieval. Experimental results show that ROUTELLM achieves 87.13% event-level accuracy and 94.65% message-level accuracy, outperforming the strongest baselines by 55.30% and 68.50%, respectively. We open-source the verified routing anomaly benchmark, fine-tuned model, and implementation code to support future research on BGP security.
Read the full abstract

All authors Libin Liu, Wenzhou Yang, Li Chen, Dan Li, Xiuting Xu

Machine Learning

SAGE: Stability-Aware Graph-Based Ensemble Feature Selection for Explainable Postpartum Depression Risk Prediction

Md. Rokon Islam Emon, Syed Shariar Alam Shuvo, Shahriar Siddique Ayon et al. (+2 more)

Postpartum depression (PPD) poses a major burden on maternal and child health, especially in low- and middle-income countries where prevalence exceeds 19%. Despite advancements in machine learning for PPD prediction, current approaches are limited by opaque global explanations that lack clinical usefulness at the patient level, unstable feature selection, and poor generalization under class imbalance. We propose SAGE, a Stability-Aware Graph-Based Ensemble feature selection system that incorporates both local explainable AI and a genetically optimized artificial neural network (GA-ANN). Using a primary cohort of 766 postpartum women, SAGE combines information-theoretic relevance, PCA-based structure, and graph-based interactions with bootstrap stability weighting to identify robust and non-redundant predictors. The GA-ANN architecture, optimized using a genetic algorithm and enhanced with GAN based oversampling, achieved strong performance with 87.96% accuracy, 86.32% F1 score, and 0.88 AUC using only 16 features, outperforming baseline and other feature selection methods. Psychological and socioeconomic factors such as EPDS score, PHQ-9 score, feelings about motherhood, and abuse history are the main predictors, while demographic factors have less influence. The LIME-based explanations allow instance-based insight into selected features from the graph, enabling personalized risk assessment. The findings make SAGE a scalable, interpretable, and clinical tool for early identification of PPD in health-care limited resources.
Read the full abstract

All authors Md. Rokon Islam Emon, Syed Shariar Alam Shuvo, Shahriar Siddique Ayon, Abdullah Al Mamun, Ahnaf Atef Choudhury

Machine Learning

CatchBench: When Can an Agent Failure Be Caught?

Yue Zhao, Mengyuan Li, Ruolin Li et al. (+5 more)

When can an agent failure be caught? A weak audit score alone cannot identify whether the record or the method is limiting. CatchBench therefore puts one auditor's question to three information states: the declared configuration before a run (PRE), a growing prefix of its trace (LIVE), and the finished trace (POST). Prior benchmarks fix one of these states or vary the telemetry; to our knowledge none scores all three under one task-method interface. Each state admits different questions, so seven task contracts carry their own labels and metrics rather than one leaderboard. Four are evidential; three are Gold-derived mechanism diagnostics. The release scores 72 entrants, from rule scanners and structural models to eleven LLM judges across nine model families (GPT, Claude, Gemini, Gemma, Llama, Qwen, DeepSeek, Mistral, Nova), over 1187 declared configurations and 1162 recorded runs. Every recorded comparison is published as a measured difference with its interval, uncorrected, and no board declares a winner it cannot show. The three sharpest results cut against our own data. One rule reads declaration order alone and reaches a perfect F1 on one of six configuration sources, so a score there measures how the corpus was built. Our admissibility bar then rejected one injected substrate and withheld evidential status from the other. A published structural gain also turns on which size reference it is measured against. A benchmark number is therefore not interpretable until the process behind its labels is published and tested for the shortcut it may leave. We report all three, and regenerate every ordering from released predictions with no model call.
Read the full abstract

All authors Yue Zhao, Mengyuan Li, Ruolin Li, Prince Zizhuang Wang, Shuli Jiang, Linsey Pang, Xiongye Xiao, Xiyang Hu

Machine Learning

Change Detection in Probability Flow ODE: Online Testing in Diffusion Latent Spaces

Artem Kraevskiy and Artem Prokhorov

A rapidly growing range of sequential data tasks, such as identifying trend reversals in financial markets, auto-segmenting video and audio recordings, detecting changes in movement direction from motion sensors cannot be fully addressed without detection of distributional shifts in time-ordered data. We consider a sequential change-point detection problem where the conditional density switches at an unknown time, yet neither the pre- nor post-change distribution admits a closed-form. Classical likelihood-ratio statistics are inapplicable in this settings. A conditional diffusion model, trained on pre-change-point data with a frozen context encoder, defines a deterministic bijection via the probability flow ODE. Pre-change observations are mapped onto standard Gaussian latent variables. Post-change observations, processed through the same frozen map, deviate from this reference. We employ the Maximum Mean Discrepancy as the test statistic, derive closed-form expressions for its components under the Gaussian null, and establish its asymptotic distribution as a degenerate U-statistic. Afterwards we apply an online detection procedure of Shiryaev–Roberts to the resulting statistic with exact threshold calibration. The method detects arbitrary distributional shifts, including covariance rotations and higher-order structural breaks, without parametric assumptions on either regime.
Read the full abstract

Computation and Language

DIAG: Diagnostic Iterative Alignment and Generation for Data-Efficient Mathematical Preference Distillation

Guhan Chen, Songtao Tian, Bohan Li et al. (+3 more)

Iterative preference optimization is essential for aligning Large Language Models on mathematical reasoning tasks, yet its efficiency is often throttled by signal scarcity: as the model improves, static problem sets become increasingly mismatched to the model's evolving competence, producing rollouts that are either too easy or too hard and therefore non-informative, which leads to a scarcity of valid preference pairs. We propose DIAG, a Diagnostic Iterative Alignment and Generation framework that adaptively reshapes the practice distribution to increase informative supervision and focus training near the student's current competence boundary. DIAG consists of two phases: (1) diagnosing valid preference-pair yield to calibrate the exploration-exploitation trade-off and allocate topic quotas via an Empirical Bayes shrinkage estimator, thereby prioritizing high-yield concepts; and (2) generating targeted practice, where a teacher synthesizes variants from the student's failure traces. We further provide a theoretical view interpreting DIAG as a teacher-mediated approximation to KL-regularized reweighting of the practice distribution toward the student's competence boundary, where valid preference-pair yield is maximized. Experiments show that DIAG boosts yield across iterations and delivers stronger reasoning performance under an iso-effective training budget, demonstrating that it can distill more informative preference supervision for mathematical reasoning.
Read the full abstract

All authors Guhan Chen, Songtao Tian, Bohan Li, Hejin Wang, YeXin Xie, Zixiong Yu

Machine Learning

Contrastive Representation-Guided Genetic Minority Oversampling for Imbalanced Time-Series Classification

Wenbin Pei, Yunrong Hao, Zhen Liu et al. (+4 more)

Real-world time-series classification tasks often exhibit class imbalance, which can be extremely severe in some applications. To avoid training biased classifiers on imbalanced data, sampling is one of the most popular data pre-processing techniques because of its classifier-agnostic nature. However, due to the complex temporal dependencies in original time-series data and the scarcity of minority-class samples, existing sampling methods, including interpolation-based oversampling methods and deep learning-based generative models, usually suffer from limited generalization and poor diversity when generating new time-series samples. This paper proposes a Frequency-domain representation-guided Multi-tree Genetic Programming-based oversampling approach (FreMGP) to imbalanced time-series classification, where each individual represents a set of synthetic samples for the minority class. A frequency-domain class-discriminative representation module based on contrastive learning is also developed, guiding the evolutionary search toward high-quality synthetic time-series samples. Experiments on imbalanced time-series datasets demonstrate that FreMGP outperforms existing oversampling methods and consistently improves the performance of different classifiers, including both general machine learning and deep learning models.
Read the full abstract

All authors Wenbin Pei, Yunrong Hao, Zhen Liu, Guan Wang, Bing Xue, Yiu-Ming Cheung, Qiang Zhang