Peer Revenue Fully funded

Papers

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

Computer Science

cs Watch Computer Science

Saturday 10 October

Computer Vision

TartanMatch: Towards Universal Dense Correspondence Across Modalities

Hyeokjoon Kwon, Jiting Cai, Ruogu Li et al. (+7 more)

Robotic platforms combine multi-modal sensors to operate across diverse conditions, but most dense correspondence methods are limited to RGB-RGB or a small set of modality pairs. Training a model for each modality pair scales poorly with the number of sensors and forgoes potential positive transfer across modality pairs. We introduce TartanMatch, a unified model for dense correspondence across all 25 ordered pairs among RGB, event, thermal, depth, and projected LiDAR. TartanMatch adapts an RGB-pretrained correspondence model to all modality pairs within one shared network using lightweight modality adaptation and a mixture of real and synthetic data. On zero-shot real-world benchmarks, TartanMatch reduces Endpoint Error (EPE) over the strongest baselines by 61.9% for cross-modal matching and 49.6% for same-modal matching. We further show that joint training across all modality pairs improves average matching accuracy over pair-specific training, especially on challenging cross-modal pairs. These results demonstrate that a single model achieves broad multi-modal coverage and state-of-the-art matching accuracy.
Read the full abstract

All authors Hyeokjoon Kwon, Jiting Cai, Ruogu Li, Kritan Bhandari, Geethika Hemkumar, Parv Maheshwari, Yuheng Qiu, Yuchen Zhang, Sebastian Scherer, Wenshan Wang

Computer Vision

Spatiotemporal Recognition of Abdominal Wall Layers During Optical Trocar Entry

Shreeram Athreya, Andrew Melehy, Carter Prentice et al. (+4 more)

Objective. To evaluate whether spatial context and temporal modeling improve tissue recognition during optical trocar entry, where multiple abdominal-wall tissues may be visible simultaneously. Methods. We retrospectively analyzed 71 recordings with 1,516 annotated keyframes and 29,151 clinician-annotated sectors. Each frame was divided into 28 polar-grid sectors assigned to nine tissue classes. Color, neighboring-sector, and positional features were used by a gradient-boosted emission classifier. The full pipeline added learned temporal smoothing, spatial regularization, an anatomically ordered hidden Markov model, and posterior blending. Five-fold cross-validation was grouped by recording, with cross-fitting to prevent within-recording leakage. Primary evaluation used clinician-derived targets; ablations assessed classification, probability quality, spatial consistency, and peritoneum-or-deeper onset timing. Results. The complete pipeline achieved accuracy 0.646, macro-F1 0.507, and macro-AUROC 0.882, versus 0.600, 0.440, and 0.861 for emissions alone. Macro-F1 improved by 0.066 across all five folds. Label changes decreased from 66.2 to 19.5 per sector-minute, and median onset error decreased from 15.58 to 2.45 seconds. Frames with a tissue-depth-code span of at least three decreased from 53% to 26%, versus 22% for clinician annotations. Performance remained limited for preperitoneal fat and bowel, and the full model retained a 44% premature-onset proportion. Conclusions. Combining appearance, spatial context, and temporal constraints improved retrospective tissue recognition and onset localization. Tissue-specific limitations, residual timing errors, and reliance on future observations warrant external validation and prospective evaluation of causal models before clinical use.
Read the full abstract

All authors Shreeram Athreya, Andrew Melehy, Carter Prentice, Michael Robinson, Corey Arnold, James Wu, William Speier

Information Retrieval

EVISTA: Unified Multimodal Video Search with Evidence-Aware Temporal Path Optimization

Minh-Huy Tran, Van-Thinh Vo, Minh-Khoi Nguyen et al. (+3 more)

In the era of big data, precise event retrieval from large video collections has become increasingly important and challenging. In particular, locating multiple events from the same video in their temporal order is difficult when different events are described by different types of evidence, such as visual content, on-screen text, and spoken words. We develop EVISTA, a unified multimodal video retrieval system for the Ho Chi Minh City AI Challenge 2026, which integrates visual-semantic, OCR, ASR, object, and metadata search over a shared keyframe index, and propose TEMPO-P, an evidence-aware temporal path optimization method for ordered multi-event retrieval. Building EVISTA for this task reveals two limitations of independent event retrieval: a relevant video may be missed when one event is weakly retrieved, and independently retrieved event candidates may be temporally inconsistent or unable to represent events defined primarily by text or speech. TEMPO-P addresses these limitations by aggregating candidate videos across events and modalities, jointly scoring keyframes using visual, OCR, and ASR evidence, and selecting a compact temporally ordered path within each video through dynamic programming. On five organizer queries and 36 additional multi-event queries, TEMPO-P matches visual-only temporal alignment on visually described events (R@1 0.42 for both) and retrieves queries containing text-defined events, which visual-only alignment cannot represent (R@1 0.38). TEMPO-P is integrated into EVISTA as its ordered-event retrieval mode.
Read the full abstract

All authors Minh-Huy Tran, Van-Thinh Vo, Minh-Khoi Nguyen, Duy-Tan Nguyen, Anh-Quan Nguyen-Tran, Loi Nguyen Khanh

Multimedia

PAG-Agent: Zero-Shot Personalized Music Album Generation via Aesthetic Profile Distillation

Yifeng Mao, Ziye Wang, Yutong Shen et al. (+2 more)

Large Music Models (LMMs) can synthesize high-fidelity audio and support increasingly flexible prompt control, yet modeling the subjective preferences of an individual listener remains underexplored. We present PAG-Agent, a zero-shot multimodal framework that uses an explicit Personal Aesthetic Profile to bridge user preference inference and music generation control. A multimodal LLM distills favorite-song audio and contextual user information into this structured representation, which a planning LLM translates into generation instructions for existing music synthesizers. We further introduce PA-Eval, which evaluates personalization through the Aesthetic Consistency Score (ACS) for target-user alignment and the Aesthetic Specificity Index (ASI) for cross-user specificity. Experiments with Personal-100 on multiple MLLM and music-generation backbones show consistent improvements over generic and direct conditioning. A 50-participant follow-up study further shows a correlation $r=0.64$ between ACS and subjective preference.
Read the full abstract

All authors Yifeng Mao, Ziye Wang, Yutong Shen, Feiran Liu, Wenjuan Han

Artificial Intelligence

MontageFlow: Physically Valid High Fidelity EEG Generation

Sudarshan Regmi, Nabaraj Subedi, Arvind Pillai et al. (+6 more)

Generative modeling offers a promising solution to the scarcity of labeled clinical electroencephalography (EEG) data under strict privacy constraints. Although recent generative models report substantial improvements in generation fidelity, we show that these gains conceal a categorical failure. EEG is not an arbitrary multichannel signal: each channel records the voltage difference between two scalp electrodes. So, real recordings satisfy exact linear identities among their channels. Current generators invariably violate these identities, yet this has gone unnoticed. We therefore propose MontageFlow, a flow-matching model that enforces these identities by restricting its output to signals that satisfy them. We find that ensuring validity improves fidelity too. Furthermore, to retain the EEG characteristics that oversmoothing washes out, we also condition the model on a physiological state vector encoded from the whole EEG window. For generation, this vector is drawn from a prior fitted in latent space. Across 3 large-scale benchmarks, our model improves TS-FID by 1.6-3.6$\times$ over the closest rival while ensuring validity.
Read the full abstract

All authors Sudarshan Regmi, Nabaraj Subedi, Arvind Pillai, Yu Yvonne Wu, Yuliang Chen, Michael V. Heinz, Lisa Marsch, Nicholas C. Jacobson, Andrew Campbell

Systems and Control

Encrypted collision avoidance maneuver via variational optimization

Yeongjun Jang, Jihoon Suh, Kenshiro Oguri et al. (+1 more)

We propose an encrypted collision avoidance maneuver (CAM) design protocol using homomorphic encryption (HE) that enables operators to outsource CAM design to an untrusted server without revealing their private covariance. To this end, we reformulate the constrained CAM optimization as a sampling based estimation problem via a variational approach, so that the private covariance dependent terms can be efficiently evaluated under HE. The protocol requires only a single round of communication, and experiments on six real-world conjunction data messages demonstrate improved feasibility and reduced fuel consumption compared with CAMs designed using public covariance.
Read the full abstract

All authors Yeongjun Jang, Jihoon Suh, Kenshiro Oguri, Takashi Tanaka

Machine Learning

Rethinking Activation Functions: Reducing Bias Can Improve Learning

Zirui Peng, Heyi Zheng and Ziming Liu

Many widely used activation functions, including ReLU, GELU, Swish, and Sigmoid, produce predominantly positive outputs, resulting in a nonzero post-activation mean that we term activation bias. Despite its ubiquity, the effect of activation bias on learning dynamics remains poorly understood. Using controlled models, we show that activation bias accelerates initial loss reduction but is accompanied by overshooting, non-smooth trajectories, and a steeper loss landscape. This early advantage also coincides with the model's use of task-relevant information encoded in the activation bias component. In contrast, reducing activation bias slows initial learning but ultimately yields a lower final loss. Experiments on larger vision and language models exhibit a similar pattern: smaller activation bias is associated with better late-stage performance. Thus, this seemingly minor property can substantially redirect learning and warrants explicit consideration in future activation function design.
Read the full abstract

Computer Vision

DSR-Net: Learning Dynamic Skeletal Relations for 3D Human Pose Estimation

Fan Li, Jian Xiang, LinLin Xue et al. (+1 more)

3D human pose estimation requires accurate modeling of motion-dependent skeletal structures and inter-joint dependencies. Existing methods typically rely on fixed skeletal topologies in Graph Convolutional Networks (GCNs) or implicitly capture joint relations through attention mechanisms, limiting their adaptability to diverse motion patterns. To address this issue,we proposeDSR-Net, a dynamic structural representation learning framework for 3D human pose estimation. Specifically, a Dynamic Skeletal Relation (DSR) module is introduced to learn adaptive inter-joint dependencies beyond predefined skeletal connections. Based on the learned relations, a hierarchical relation-aware fusion strategy is developed to facilitate effective interaction between structural and temporal representations. In addition, a lightweight Residual Skeletal Recalibration Module (RSRM) is designed to enhance the stability of structure-aware features with minimal computational overhead. Extensive experiments on Human3.6M and MPI-INF-3DHP demonstrate that DSR-Net achieves MPJPEs of 37.9 mm and 14.9 mm, respectively, consistently improving over strong baselines. The results validate the effectiveness of dynamic skeletal relation modeling for robust 3D human pose estimation.
Read the full abstract

All authors Fan Li, Jian Xiang, LinLin Xue, Yuwei Gao

Machine Learning

DEFT: Disentanglement-Enhanced Fine-Tuning for EEG Foundation Models

Yuqiu Deng, Muyun Jiang, Zongpeng Zhang et al. (+8 more)

EEG foundation models (EFMs) have improved EEG representation learning by transferring knowledge from large-scale multi-subject pretraining to downstream tasks. However, their pretrained embeddings often retain substantial subject-related variation, placing an additional burden on the downstream classifier, especially in cross-subject settings. To address this issue, we propose Disentangled EFM Fine-Tuning (DEFT), a plug-and-play adapter for EFM fine-tuning. DEFT encourages branch disentanglement of pretrained tokens into task-oriented content and subject-consistent style, then performs downstream prediction from the content branch. It instantiates this factorize-before-classify design with recursive Gaussian refinement, temporal-variance regularization, subject-aware contrastive learning, and reconstruction. Experiments across multiple EEG datasets and four EFM backbones show that DEFT improves matched fine-tuning baselines. Further ablations and analyses support the intended content/style branch organization.
Read the full abstract

All authors Yuqiu Deng, Muyun Jiang, Zongpeng Zhang, Mingqing Xiao, Yansen Wang, Peiliang Gong, Xinliang Zhou, Yi Ding, Ziyu Jia, Cuntai Guan, Chenyu Liu

Artificial Intelligence

Reels-RSI: Program-Level Self-Improvement for Code-Rendered Explainer Videos

Wei Lin

Explainer videos – a worked geometry problem, why the sky is blue, how a dynasty fell – are usually one more target for pixel video generation. We argue they are a different kind of artifact: a program (script, storyboard and per-frame animation code) that a deterministic renderer turns into frames. A program can be read, diffed, tested and audited; pixels can only be watched. Reels-RSI is an open-source reel director for any agent harness; its self-improvement happens at the program level rather than in weights or prompts. Every revision pass is logged with a code snapshot; a retrospective pairs each check finding with the diff that fixed it and proposes lessons; a lesson that a static check can catch is compiled into a rule with a must-fail and a must-pass example, so the memory is unit-tested; and a rule learned today runs over everything made before it. A bounded, benchmark-gated step lets an agent rewrite the director's playbook, kept only when blind pairwise judgments on held-out topics prefer it; nothing enters memory without a human decision. Across 111 reels – a field study, two playbook evolutions, a 2x2 memory ablation, a weaker director, a 48-reel learning curve and a judge-reliability study – we find that the rule learned in the field caught four latent defects in frames authored before it existed and none after; that rules are an audit for a strong director (eight unguarded reels, no violation) and a guard for a weaker one (thirty violations unguarded versus five); that lessons shorten revision loops but do not compound or move the judge; and that the first rewrite's 11–1 verdict was a position bias in our vote design (judges pick the second-shown reel 62–81% of the time), masking scripts that traded thirteen facts for craft. We document four failure modes of the preference signal, which check caught each, and the fixes. Code, rules, lessons and data are public.
Read the full abstract

Machine Learning

A Gated Catchment Hydrology Model (GCHM) for Physically-Interpretable Rainfall-Evapotranspiration-Runoff Simulation Across Diverse Hydroclimatic Regimes

M Jawad, HV Gupta, MA Farmani et al. (+2 more)

Recent advances in machine learning have improved rainfall-runoff prediction, yet most data-driven models remain difficult to interpret and do not explicitly enforce physical conservation laws. We present the Gated Catchment Hydrology Model (GCHM), a mass-conserving architecture based on the Mass-Conserving Perceptron (MCP). GCHM uses five storage states representing canopy interception, snow, soil moisture, groundwater, and streamflow generation. Constrained gates govern precipitation partitioning, evapotranspiration, infiltration, seepage, runoff, and baseflow while learning context-dependent process relationships. We evaluate GCHM across 50 CAMELS catchments spanning snowmelt-dominated, recent-rainfall, historical-rainfall, and arid regimes, using NOAA AORC meteorological forcing and remotely sensed vegetation and land-surface data. Performance is assessed using the Jawad-Kling-Gupta Efficiency (JKGE) metric, which accounts for stationary and non-stationary hydrologic behavior. We compare the full architecture with ablated variants and recurrent neural network benchmarks. GCHM reproduces streamflow dynamics across diverse hydroclimatic regimes, including arid catchments, while maintaining interpretable states and fluxes. Ablation experiments show that simplified architectures may perform adequately under wet conditions but struggle to represent flow persistence and recession during dry periods, when groundwater storage sustains low flows. Learned gates recover hydrologically plausible relationships governing snowmelt, runoff, seepage, and evapotranspiration. GCHM combines competitive predictive performance with mass conservation and interpretability, providing a foundation for hydrologic modeling and counterfactual analysis.
Read the full abstract

All authors M Jawad, HV Gupta, MA Farmani, A Behrangi, GY Niu

Robotics

Multi-modal Representation Fusion for Long-term Microsurgical Anastomosis Trajectory Anticipation

Yuxuan Liu, Yating Luo, Yunfei Luan et al. (+4 more)

Microsurgical anastomosis is one of the most challenging and sophisticated procedures for surgical robotics, requiring accurate manipulation of surgical instruments within a limited space to achieve precise operations. Accurate surgical trajectory anticipation is essential for surgical scene understanding, intraoperative planning, robotic manipulation, and reliable behaviour analysis. However, existing approaches mainly focus on features extracted from surgical videos and historical trajectories, while overlooking rich semantic and motion information that can provide more discriminative multi-modal representations for complex surgical instrument-tissue interactions. In this work, we propose a cross-modal feature fusion framework for long-term 2D and 3D microsurgical anastomosis trajectory anticipation. The proposed framework consists of a multi-modal representation extractor and a cross-modal feature fusion network. Semantic recognition of surgical objects and consecutive motion estimation are incorporated as multi-modal visual cues, providing complementary spatial and temporal guidance for instrument-tissue interaction characterization. A coarse-to-fine progressive fusion strategy with a long-short-term memory mechanism is introduced to capture temporal dependencies step by step. The training and evaluation are conducted on our established robotic platform and a comprehensive dataset containing both phantom and ex-vivo surgical scenarios is constructed. Extensive quantitative and qualitative experiments demonstrate that the proposed framework consistently outperforms existing methods and exhibits improved robustness across different surgical scenes, highlighting its potential for both intelligent robot-assisted and autonomous surgical systems.
Read the full abstract

All authors Yuxuan Liu, Yating Luo, Yunfei Luan, Xinyao Zhou, Yuyang Zhuge, Yao Guo, Guang-Zhong Yang

Artificial Intelligence

HiPPT: Physiology-Grounded Wearable PPG Representation Learning via Multi-Scope Text Alignment

Jiaqi Wang, Wei Chen, Xiaoyu Li et al. (+7 more)

Reusable wearable PPG representations should capture local pulse morphology and broader physiological regularities. Existing pretraining objectives, however, usually apply supervision at the recording or pair level, overlooking that different concepts become reliable over different scopes of waveform evidence. We propose HiPPT, a physiology-grounded framework that matches each supervision source to its appropriate evidence scope. We construct a PPG-Text corpus of over 4 million wrist-worn recordings from 202K users, pairing recordings with waveform-derived morphology and metadata-derived context descriptions. HiPPT combines record-level morphology alignment, which grounds individual recordings in pulse characteristics, with cross-recording context alignment, which aggregates recordings sharing the same metadata tuple to capture context-consistent regularities. Waveform-guided text modeling further recovers masked contextual concepts from PPG patch representations, providing fine-grained waveform-text supervision. Across six downstream tasks spanning blood pressure, vascular stiffness, physiological attributes, and cross-dataset heart-rate estimation, HiPPT achieves the best result on the primary linear-probing metrics. The aligned space also supports zero-shot profiling of age group, sex, and BMI category, individually and jointly, with performance improving as more recordings are aggregated. These results show that evidence-scope matching yields transferable and semantically accessible wearable PPG representations. Code and pretrained weights will be released.
Read the full abstract

All authors Jiaqi Wang, Wei Chen, Xiaoyu Li, Lexian Xia, ShuaiLong Tang, Chenran Zhang, Donglin Xie, Guangpu Zhu, Yelei Li, Yi Zhou

Cryptography and Security

Names Are Not Objects: Object-Bound Confinement for Compromised AI Coding Agents

Daniel Commey

Coding agents read repositories and web pages that anyone can write, and then act with their user's authority. Prompt-injection defenses make it less likely that the model is steered but do not prevent it, so the system around the model must contain an agent that is already compromised. Many exploits against deployed coding agents share one cause: a check approves a name, such as a path, an argument vector, or a directory, and a later step maps that name to a different object: the file behind a symlink, the behavior an option selects, or a repository that git discovers on its own. We present Zero-Trust Agent Cells (ZTAC). A cell runs the agent in a kernel sandbox whose only route to files, programs, and the network is a socket to a broker. The broker resolves each request to the object it will act on, decides on that object, and checks at use that it is acting on the object it authorized. Programs that the broker starts run in a sandbox compiled from the same policy, and approvals are bound to the resolved object and can be used once. Our macOS prototype has 3.2k lines of trusted Rust code, excluding dependencies. We evaluate it against 74 attacks with ground-truth oracles, including replays of 10 publicly disclosed incidents. A tool allowlist loses 66 of them, and an allowlist combined with the kind of command sandbox that deployed agents use loses 56. ZTAC loses 2, both of which encode a secret into traffic to an allowed endpoint, and holds 14 for review. It completes 43 of 46 benign operations, with 8 approval prompts, and 4 of 7 workflows. A no-op brokered request has a median latency of 4.0 ms, and the spawned programs we measured take 8.5 ms to 18.4 ms longer than without ZTAC.
Read the full abstract

Artificial Intelligence

AlignPoison: Conditional Targeted Poisoning of Generative Recommenders via Decoding-Aligned Prefixes

Zhuoxuan Zhang, Jinhao Duan, Xinyu Zhao et al. (+7 more)

Generative recommendation models based on autoregressive decoding have been adopted as alternatives to classical ranking-based systems. While their modeling flexibility has been widely studied, their resilience to data poisoning remains largely unexplored. In this work, we ask: how susceptible are generative recommenders to conditional targeted poisoning? Under a realistic setting where an adversary can inject limited malicious interactions and query a recommendation API as a black box, our empirical study shows that generative recommenders are vulnerable: injecting fewer than 1% synthetic interactions significantly increases the likelihood of promoting malicious targets under the trigger. To characterize this vulnerability, we analyze the synthesis of malicious interactions from two perspectives: (i) decoding alignment and (ii) prefix popularity. We observe that short, context-aligned prefixes that are both common under the model's induced transition dynamics and strongly linked to a frequent trigger consistently amplify targeted promotion. Motivated by this analysis, we develop AlignPoison, a black-box framework that discovers and samples context-aligned prefixes from API outputs. We conduct experiments on benchmarks in unimodal and multimodal generative recommendation settings. Results show that these prefixes outperform competitive baselines, improving ASR lift by up to 16.3 percentage points and highlighting a decoding-dependent, context-sensitive poisoning vulnerability in generative recommendation models.
Read the full abstract

All authors Zhuoxuan Zhang, Jinhao Duan, Xinyu Zhao, Jinduo Guo, Shuai Shao, Rui Li, Luke Simon, Zhun Deng, Tianlong Chen, Bo Sun

Databases

TurboProm: Low Cost and High Performance Metrics Observability at Scale

Milind Srivastava, Zeying Zhu, Peilin Xin et al. (+3 more)

Many large enterprise and cloud deployments rely on metrics observability solutions (e.g., Prometheus) to monitor key performance indicators of system health (e.g., CPU, memory, network, app-level statistics). Monitoring and analyzing these metrics presents a significant challenge in terms of cost-latency tradeoffs at scale. Ideally, system operators would like immediately deployable and backwards compatible solutions to improve the cost-latency tradeoffs without significant impact on the fidelity of their observability applications. Unfortunately, existing solutions including state-of-art timeseries databases and custom approximate querying solutions fail on one or more aspects. In this paper, we present the design and implementation of TurboProm, a backwards-compatible drop-in accelerator for metrics observability deployments. TurboProm recasts metrics analytics tasks using a semantic-preserving summary view rather than classical query-centric view. Instead of estimating query results on raw timeseries metrics data, TurboProm uses semantic-preserving summaries that enable high-fidelity analytics with significant cost-latency improvements. We present a practical implementation of TurboProm that can be retrofitted to any existing observability deployment. We evaluate TurboProm on diverse real and synthetic workloads against state-of-art solutions and show that it can provide significant reduction in query latency and cost. TurboProm is open-source at https://github.com/ProjectASAP/ASAPQuery.
Read the full abstract

All authors Milind Srivastava, Zeying Zhu, Peilin Xin, Yancheng Yuan, Zaoxing Liu, Vyas Sekar

Robotics

From Field to Planning: Learning Temporal Polar Gradient Fields for Vision-based AAV Trajectory Planning in Dynamic Environments

Haowen Gao, Zhan Chen, Yinuo Xu et al. (+3 more)

Autonomous Aerial Vehicle (AAV) trajectory planning requires real-time and accurate safety gradient guidance, especially in dynamic environments. Existing methods typically rely on static maps and dynamic obstacle tracking to construct gradient fields, imposing heavy computational burdens and yielding conservative trajectories. To address these limitations, we propose a two-stage Field-to-Planning (F2P) learning framework to provide accurate and efficient safety gradients for trajectory planning in dynamic environments. In the first stage, we introduce an Ego-centric Polar Occupancy (EPO) representation that naturally matches the geometry of the onboard camera frustum, while supporting unstructured scene modeling. Subsequently, we formulate a Temporal Polar Gradient Field (TPGF) via multi-kernel separable Gaussian convolution to provide unified safety gradients, without explicitly distinguishing between static and dynamic obstacles. To mitigate the inherent spatial ambiguity introduced by applying convolutions within the polar grid, we propose an ESDF-guided offline learning strategy that incorporates geometric priors into TPGF. In the second stage, we employ the calibrated TPGF to guide the trajectory planning policy in a self-supervised learning manner. Comparative results with other approaches demonstrate the superiority of our method. Extensive real-world experiments within various cluttered dynamic environments validate the real-time performance and robustness on resource-constrained onboard systems.
Read the full abstract

All authors Haowen Gao, Zhan Chen, Yinuo Xu, Yifeng Niu, Mengyun Wang, Chao Yan

Multiagent Systems

Optimize Once, Execute Fast: Latency-Aware Multi-Agent Workflow Learning for Recurrent Queries

Enpei Zhang, Feiyu Qu, Zheng Huang et al. (+3 more)

Large Language Model-based Multi-Agent Systems (LLM-based MAS) have shown remarkable success in solving complex tasks by coordinating specialized agents through multi-step workflows. To overcome the high cost and specificity of manually designed workflows, recent research has shifted toward learning them automatically. However, a key limitation remains: while agent calls introduce significant latency due to model inference time and service congestion, most automated methods optimize solely for downstream performance, ignoring execution time (makespan). This issue is amplified when workflows are reused across recurring queries, making latency accumulate over time. This limits deployment in recurrent applications such as AI customer support and AI cloud troubleshooting, where users expect fast responses. To bridge this gap, we introduce a new problem, termed latency-aware workflow generation, where the objective is to minimize workflow makespan while aiming to retain downstream performance. We propose LAWA (Latency-Aware Workflow optimizAtion), a novel framework that reduces makespan via theoretically grounded graph edits targeting critical-path bottlenecks. By unifying a graph generator with this graph-editing procedure, LAWA supports both de novo workflow generation and refinement of existing ones. Empirical results across seven benchmarks demonstrate that LAWA significantly reduces makespan while achieving competitive task performance, supporting efficient reuse of multi-agent workflows for recurrent queries.
Read the full abstract

All authors Enpei Zhang, Feiyu Qu, Zheng Huang, Dawei Zhou, Elynn Chen, Yujun Yan

Computation and Language

AphaVoice: Text-to-Speech Model for Aphasia Patient Simulation

Al Varrel Putra Kusuma, Fernando Bello and Joshua Brown

While language therapy is the primary treatment for post-stroke aphasia, limited clinical resources often restrict patient access to proper care. Addressing this gap requires reliable training simulations for medical professionals. However, current AI efforts focus almost exclusively on speech processing, leaving speech generation largely unexplored. This study introduces AphaVoice, a novel text-to-speech (TTS) framework explicitly engineered to synthesize highly realistic aphasic speech. Evaluated against state-of-the-art TTS systems, AphaVoice demonstrates a superior ability to capture the clinical feature of dysfluency, outperforming existing models in temporal metrics while consistently maintaining speaker identity. By leveraging latent space shifting, the model also supports multi-speaker generation without sacrificing phonetic realism. Ultimately, AphaVoice provides a scalable, high-fidelity tool for medical training and clinical simulation related to aphasia.
Read the full abstract

Robotics

Shared-Control Teleoperation of Omnidirectional Aerial Robots for Continuous Valve Rotation

Jinjie Li, Yicheng Chen, Haokun Liu et al. (+1 more)

Omnidirectional aerial robots offer full 6-DoF independent control over position and orientation, making them popular for aerial manipulation. Although there have been advancements in robotic autonomy, human operation remains essential in complex aerial environments. Previously, we proposed an aerial teleoperation system that brings the rotational flexibility of human hands into the unbounded aerial workspace, which was evaluated through a vertically mounted valve-turning task. However, due to the limited range of human forearm's motion, the robot could not continuously rotate the valve, hindering its application in industry. In this work, we propose an approach to initiate continuous rotation when the forearm angle exceeds a threshold. This switch of control authority exemplifies the concept shared control from human-robot interaction, marking a further step in aerial teleoperation.
Read the full abstract

All authors Jinjie Li, Yicheng Chen, Haokun Liu, Moju Zhao

Software Engineering

What Counts as the Same Task? Executable Contracts for Robustness Evaluation of Tool-Using Agents

Shaikh Akib Shahriyar, MD. Akil Raihan Iftee, Armon Barton et al. (+1 more)

Robustness tests for tool-using agents often change the agent's environment, for example by hiding a hostile note in an invoice, and then judge the agent by what it does. The result tells us about the original task only if the changed test case is still a valid test of that task. Many evaluations decide this with weak rules, such as accepting any well-formed edit or any edit that stays close to the original in embedding space. We propose executable task contracts. A contract states which facts define a task, which edits are allowed, and what finishing the task means, and it checks each changed test case before the agent runs. We compare validity rules by scoring the same 14,336 stored agent runs under each rule. Across four encoders, embedding thresholds allowed 75-100% of edits that changed the task, such as swapping the payee, yet rejected 24-45% of valid hostile notes. With a MiniLM cosine threshold, Mistral appeared vulnerable on all 64 tasks, but only 26 had a successful valid attack. Replaying a saved solution and allowing edits to benchmark fields fail in similar ways. Evaluations should state, and check, what counts as the same task.
Read the full abstract

All authors Shaikh Akib Shahriyar, MD. Akil Raihan Iftee, Armon Barton, Matthew Wright

Computation and Language

Scale, Drivers, and Limits of Representational Alignment Across Large Language Models

Jialin Wu and Meenakshi Khosla

Comparing large language models can reveal shared representational structure and systematic differences between them. However, aggregate similarity measures can obscure how agreement varies across geometric scales and which linguistic properties support it. We introduce two complementary methods to resolve where models agree and what supports that agreement. Standard representational similarity analysis (RSA) summarizes similarity across all stimulus pairs, potentially obscuring differences in alignment between nearby and distant inputs. Neighborhood-Weighted RSA (NW-RSA) addresses this limitation by weighting stimulus pairs according to their proximity in representational space, placing alignment from local neighborhoods to global geometry on a common scale. Counterfactual RSA (CF-RSA) tests which linguistic properties support alignment by comparing intact representations in one model with representations under controlled linguistic perturbations in another. Across diverse language models, we find strong agreement in coarse representational geometry but substantial divergence in local neighborhoods. Alignment is observed both across broadly sampled natural text and within linguistic equivalence classes that preserve particular aspects of meaning or structure. Counterfactual analyses reveal selective sensitivity: changes to logical scope reduce alignment substantially more than the tested changes to hierarchical syntax, event roles, or discourse structure. Alignment also decreases when sentence structure or lexical meaning is disrupted in word lists and jabberwocky sentences, suggesting that the regularities of natural language support stronger convergence. These findings refine claims of representational universality by showing that strong overall similarity need not imply agreement in how models represent finer linguistic distinctions.
Read the full abstract

Computation and Language

EdgeLLM-Nano: Auditing Polar-Guided Key-Cache Compression and Consistency-Anchored Pruning on a 33.6 MB On-Device Language Model

S M Mahbub Murshed, Hayden Bright, Rezaul Karim et al. (+1 more)

Deploying language models (LMs) on the edge presents unique memory, latency, and power challenges absent in high-performance computing. KV-cache compression emerges as a promising approach to address these challenges. However, the effectiveness of current KV-cache compression methods has not been thoroughly examined on edge devices. Moreover, we show that existing evaluation methods do not always involve the KV-cache under test. We propose EdgeLLM-Nano, a measurement study of KV-cache compression using a nano-scale decoder-only LM (transformer) testbed that has 8.39M parameters, i.e., 33.6 MB, to enable end-to-end examination of each backend, seed, and power sample. Our results give a negative verdict for a polar-guided key-cache quantizer (round-to-nearest (RTN) control causes an order of magnitude less damage), as well as a consistency-anchored progressive weight pruner (one-shot magnitude-based pruning performs as well as, if not better). We also introduce Long-Context Decode Fidelity (LCDF) evaluation, a token-by-token examination of teacher-forced log-losses using the KV-cache under test. Unlike perplexity that gives the same 5.461 score to all methods, LCDF distinguishes different KV-cache compression backends thanks to its paired statistics across seeds and effect sizes. Our companion Raspberry Pi 5 measurement shows all compression backends we tested to be less energy-efficient per token compared to uncompressed FP16 inference. Except for KIVI that is close to lossless in terms of LCDF, our findings indicate KV-cache compression can be improved. LCDF offers a simple and effective way of shedding light on KV-cache compression methods, whose negative impacts have been overlooked by perplexity.
Read the full abstract

All authors S M Mahbub Murshed, Hayden Bright, Rezaul Karim, Ali Shiri Sichani

Machine Learning

RES-MR: Risk-Aware Reasoning for Explainable and Safe Medication Recommendation

Cong Wang, Jin Li, Shoujin Wang et al. (+3 more)

Medication recommendations seek to deliver personalized drug combinations based on patients' clinical information, where ensuring transparent decision-making and personalized safety are of paramount importance. However, existing approaches predominantly operate as “black boxes”, offering limited interpretability and hindering clinician trust. Furthermore, they typically rely on fixed, patient-agnostic safety constraints, neglecting the heterogeneity of risk tolerance across individuals, which poses significant risks to vulnerable populations. To address these gaps, we propose RES-MR, a novel Risk-aware Reasoning framework for Explainable and Safe Medication Recommendation using LLMs. RES-MR follows a two-stage training paradigm: (1) an explainable clinical reasoning distillation stage to elicit diagnostic capabilities by fine-tuning on synthesized reasoning trajectories, grounded in patient-specific knowledge from graph retrieval; and (2) a risk-aware policy optimization stage to dynamically balance therapeutic efficacy with personalized safety. This stage employs disentangled drug factors to construct patient-specific reference prototypes that capture desired therapeutic drug features and risk features to avoid. These prototypes enable risk boundary calibration and guide the model toward safe recommendations via reward shaping and clipping. Extensive experiments on benchmark datasets demonstrate that RES-MR significantly outperforms state-of-the-art baselines in terms of accuracy, safety, and explainability. Our code and data are available at: https://github.com/wangcong2001/RES-MR.
Read the full abstract

All authors Cong Wang, Jin Li, Shoujin Wang, Yishuo Li, Huilin Gu, Wenpeng Lu

Game Theory

Diffusion-Based Auctions for Multi-Winner Banner Ads

Lilian Sun, Henry Huang, Fucheng Warren Zhu et al. (+2 more)

We propose a new framework for banner ad auctions, leveraging diffusion models to allow for multiple bidders to co-win a single banner ad opportunity, and in particular influence the ad shown on the banner depending on the strength of their bids, enabling a far richer outcome space compared to standard banner ad auctions, where there is a single winner who shows their ad. In our framework, the outcomes are images (what ad to show) and each bidder expresses their preferences over outcomes by declaring their value per unit of alignment between the image chosen by the mechanism and a textual description of their desired image. Our proposed mechanism combines the advertisers' bids and textual descriptions into a score that drives the reverse process of a diffusion model. This is used to sample a set of candidate images from which the welfare maximizing one is eventually chosen. Extensive experimentation evaluates our proposed mechanism around the following axes: (1) efficiency improvements of our allocation rule relative to the single-winner allocation rule; (2) monotonicity of our allocation rule; and (3) approximate incentive compatibility when combining our allocation rule with Myerson lemma-based or Clarke rule-based payments. Improvements along all these axes are shown with the number of Monte Carlo samples. Meanwhile, these benefits are attained while preserving the image quality.
Read the full abstract

All authors Lilian Sun, Henry Huang, Fucheng Warren Zhu, Giannis Daras, Constantinos Daskalakis

Systems and Control

Spatial-Temporal Hybrid Path Planning for Multi-UAV Methane Emission Rate Quantification

Ruikun Wu, Derek Hollenbeck and Sihua Shao

Accurate emission-rate quantification of methane point sources is essential for inventory verification and leak detection. UAV-borne sensing provides high-resolution, near-source measurements, but existing quantification methods mostly follow a predefined trajectory and rely on a single UAV. Building on a source receptor matrix (SRM) estimator and empirical observability Gramian (EMGR)-based path planning, this paper proposes a spatial-temporal hybrid path planning strategy for multi-UAV methane emission rate quantification. Measurements are time-averaged, and the forward Gaussian plume model is calibrated against a filament-based plume simulator (MOABS) to reduce model mismatch. Cooperating UAVs first spread out spatially to locate the source quickly, then switch to sequentially retracing a leader trajectory with a time lag to reduce quantification variance. Simulations show that the spatial stage localizes the source markedly faster than a single-UAV baseline, the temporal stage yields the lowest variance but converges slowly, and the proposed hybrid strategy converges substantially faster than the purely temporal strategy while matching its steady-state accuracy, with a narrower error band than the purely spatial strategy. A window-length study further shows that longer time-averaging windows exhibit diminishing returns, justifying the balance between spatial coverage and temporal averaging.
Read the full abstract

Software Engineering

When Is a Reconciliation Break Real? A Temporal Correctness Contract for Streaming Financial Reconciliation

Abhishek Sharma

Reconciliation systems decide, continuously, whether money the ledger expected has arrived at the bank. On an asynchronous stream that decision is taken against partial evidence: a credit that has not appeared may be missing, or may simply not have been posted yet. Deployed pipelines settle this with a timeout or a watermark, and the exceptions are treated as findings. We give a temporal correctness contract that says when such a verdict is admissible, relative to a declared per-source lateness bound, and a checker for it that needs no ground truth. The contract separates three things an operator otherwise sees only as a rising break rate: the reconciler decided too early, an input broke the bound it declared, or the money really is gone. On workloads from a published payment simulator, the standard remedy for a stalled streaming join, an idleness timeout, introduces contract violations on 5.42% of obligations (95% CI [3.94, 6.92]) on traffic where the same job without it is exactly sound, and violations vanish once the timeout reaches the slow source's posting period, as predicted. Under a lateness shift, all four identity-based reconcilers we test raise spurious breaks on between 18.3% and 23.0% of the credits the bank did settle, while their contract violation rate stays at or below 1.01%: the checker attributes the loss to 240 bank-side and 413 ledger-side bound violations rather than to the reconcilers. Tracking one horizon per source leaves break latency 12.7% lower on average and halves its tail (p99 224 against 446 ticks) at equal soundness, though it is not cheaper at every cost setting and we report where it loses. An Apache Flink interval join, written the ordinary way, violates the contract on 14.9–20.1% of obligations. The contract is expressible as SQL over the tables a reconciliation system already keeps, agreeing with the reference implementation on all 4,395 verdicts.
Read the full abstract

Numerical Analysis

Memory-Augmented Phase-Field Modeling: Onsager Formulation, Internal-Variable Lifting, and Structure-Preserving Computation

Peng Ding, Qingxia Liu, Zhiping Mao et al. (+1 more)

In this work, we develop a general memory-augmented phase-field (MAPF) framework based on Onsager's variational principle, in which memory effects are incorporated through a general relaxation kernel while preserving the thermodynamic consistency of the underlying system. Rather than treating fractional models as fundamental formulations, we show that they can be interpreted as reduced descriptions associated with specific power-law memory kernels. The proposed MAPF equations provide a unified modeling framework for non-Markovian phase-field dynamics. To facilitate analysis and computation, we further introduce an equivalent internal-variable representation that transforms the original nonlocal-in-time dynamics into an extended Markovian gradient system. This formulation preserves key structural properties, including energy dissipation and mass conservation, and enables the development of efficient structure-preserving numerical schemes. In particular, we construct an energy-stable scalar auxiliary variable approach combined with a fast rank-one implementation that exploits the relaxation-spectrum-induced coupling structure, resulting in a computationally efficient algorithm with reduced storage requirements. The proposed framework establishes a systematic connection between memory-dependent phase-field modeling, internal-variable thermodynamics, and structure-preserving numerical computation. Numerical experiments demonstrate the accuracy, stability, and efficiency of the proposed methods for phase-field dynamics with long-time memory effects.
Read the full abstract

All authors Peng Ding, Qingxia Liu, Zhiping Mao, Zhen Zhang

Information Retrieval

Co-adaptive Rule Routing and Constraining for Structured Knowledge Retrieval

Zhisheng Qi, Haoyu Han, Jiaxi Li et al. (+9 more)

Structured knowledge retrieval acquires task-relevant evidence from structured knowledge sources for downstream tasks. Existing methods rely on unconstrained retrieval or predefined query-rule supervision, such as author-paper rules for scientific discovery and anatomy-drug rules for precision medicine. Such supervision is rarely available in practice. We propose Co-Adaptive Rule Routing and Constraining Retrieval (CoRE), which jointly learns which reasoning rule to assign to each query and how to retrieve evidence under that rule, without predefined query-rule pairs. A routing agent selects a rule, and its corresponding retriever traverses the knowledge base and ranks evidence that satisfies the rule's constraints. Because routing and retrieval are interdependent, CoRE alternates between reinforcement learning for the routing policy and contrastive learning for the rule-constrained retriever. The selected rules provide supervision for retriever training, while retrieval performance rewards the routing policy. This closed-loop process enables both components to co-adapt without explicit query-rule supervision. Experiments on STaRK-QA datasets across scientific discovery, biomedical reasoning, and e-commerce knowledge management demonstrate CoRE's effectiveness. Ablations show the benefit of co-adapting the router and retriever. Generation-based routing transfers across datasets and benefits from multi-domain pretraining followed by target-specific fine-tuning. Analysis of rule usage across queries also informs automatic rule refinement and discovery.
Read the full abstract

All authors Zhisheng Qi, Haoyu Han, Jiaxi Li, Bing He, Huiyuan Chen, Franck Dernoncourt, Ryan A. Rossi, Mahantesh M. Halappanavar, Jin Lu, Yu Zhang, Tianming Liu, Yu Wang

Computation and Language

Evaluating Bias in Chinese Large Language Models across Tasks and Registers: Task Operationalization Effects and Irony Classification Risks

Mo Zhou

In Chinese content governance, large language models are increasingly used to identify toxic and discriminatory expressions, yet both task operationalization and ironic expression can alter bias measurement readings. We conducted a preregistered multi-task behavioral audit of multiple Chinese large language models. In the content classification experiment, the core panel's classification error rate rose from 10.9% in the formal register to 23.5% in the yinyang (an echoic-irony register) version, a risk difference of +12.7 percentage points. (95% CI [+9.7, +15.7]). Inter-rater agreement was lower in the yinyang register (majority-vote kappa = 0.299), so the increase contains a component of label uncertainty propagation, but the direction of increase was consistent under both adjudicated and majority-vote reference standards. Explicit irony-aware prompts reduced the intervention panel's error rate by 9.6 percentage points. We operationalized the 29 shared proposition anchors into three task forms: social consensus estimation (Form A), high-stakes decision (Form B), and controlled association rating (Form C); independent manipulation checks found that all 58 A-C comparison units received unanimous agreement, whereas the low A-B convergence was confirmed by calibrated majority adjudication (87.8% supporting the minority judgment); on the irony-probe materials, the interactions of B and C relative to A were +0.577 and +1.121, respectively. Thus, when evaluating large language models for Chinese content governance, the effect of task operationalization on bias readings is an empirical question that requires data to answer, and safety evaluation should incorporate the ironic register as a test condition.
Read the full abstract