GAN
-
SAFESHIELD: A Decision-Organization Framework for Deployment-Time Safety of Small Language Models
Abstract
Deployment-time safety of language models is commonly implemented through runtime guardrails such as input moderation, routing, retrieval verification, and output filtering. Existing deployment frameworks provide increasingly capable mechanisms for these functions, but offer limited guidance on how the safety decisions they produce should be explicitly organized, coordinated, and audited. We formulate deployment-time safety as a decision-organization problem with two elements: responsibility-oriented decomposition of safety decisions and explicit coordination among them. We instantiate this formulation in SAFESHIELD, a deployment-time safety system for small language models that organizes four recurring decision responsibilities (admission, routing, evidence, and release) and records committed decisions in auditable Decision Traces. We evaluate SAFESHIELD through mechanism-level experiments, aggregate stage ablations, controlled coordination ablations, and a deployment-oriented stress suite. Mechanism-level results show that the instantiated safeguards provide the capabilities required by the decision process, while aggregate ablations show substantial degradation in end-to-end safety as the surrounding safety organization is removed. More importantly, dedicated coordination ablations preserve the participating safeguard mechanisms while selectively severing their dependencies: removing admission gating substantially increases false release, and withholding upstream evidence from the release decision reduces release accuracy from 96.0% to 69.5%. These results provide system-level evidence that deployment-time safety depends not only on the capability of individual guardrails, but also on how their decisions are organized and coordinated.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07276
PDF
-
Fluorescence-enhanced Whisker Array with Vision-based Deformation Analysis for Underwater Source Localization
2026-10-05 19:15:58Xiaochi Xie, Hao Li, Shixuan Zhao, Siyue Yao, Shuran Song, Mark R. CutkoskyAbstract
Deep-water biological observation is essential for understanding marine organisms and their interactions with the environment. However, conventional optical and acoustic approaches can introduce stimuli that alter animal behavior and bias biological observations. This paper proposes a fluorescence-enhanced whisker array sensing system that pinpoints underwater hydrodynamic sources through local optical readout rather than direct source imaging. Five spatially oriented whiskers, fabricated with nitinol cores and fluorescent urethane shells, are integrated with ultraviolet excitation and a monocular camera. Image enhancement and segmentation are applied to track the whisker deformation. A lightweight convolutional neural network captures temporal and cross-whisker features from 2 s sequences to estimate source localization. Pool experiments achieve a mean spatial localization error of 88 mm, with 73.5 mm in radius and $2.5^\circ$ in angle, across a test region of 600 mm with $\pm30^\circ$. Real-time localization of a moving thruster demonstrates the capability of the proposed method in dynamic scenarios, highlighting its potential for integration into underwater robots for hydrodynamic source detection, localization, and tracking in low-light environments.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07275
PDF
-
Energy-Conditioned Noise Schedule and Whitening for Spectral Diffusion
Abstract
This paper introduces an energy-adaptive noise scheduling and whitening strategy for transform-domain diffusion models. Existing spectral diffusion methods account for the non-uniform statistics of transform coefficients through coefficient scaling, normalization, or frequency prioritization, while the forward diffusion noise schedule remains largely independent of the underlying spectral-energy distribution. We investigate whether the temporal evolution of the forward diffusion process should also follow the spectral organization of natural images. The proposed formulation combines global spectral whitening with energy-conditioned noise allocation that jointly modulates the injected noise according to the energy of individual transform coefficients and an image-dependent energy path over diffusion time. The resulting forward process preserves Gaussian transitions with closed-form marginals and remains compatible with standard DDPM and DDIM procedures without modifying the diffusion architecture. Experiments on CIFAR-10 demonstrate the contribution of the proposed energy-conditioned noise schedule and spectral whitening, reducing Fréchet Inception Distance from 142.48 for a compact DCTdiff U-Net variant to 100.45.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07206
PDF
-
Responsible Institutional Analytics: Interpreting Bias with AI Support
2026-10-05 18:19:34Francielle Marques, Ariel Ortiz-Beltr\'an, Ishari Amarasinghe, Davinia Hern\'andez-LeoAbstract
Institutional Analytics (IA) dashboards inform decision-making in higher education, yet data limitations, constraints in analytical techniques, and missing contextual information often affect their interpretation. To support more responsible interpretation of IA, we introduce FACTRIA, a framework that organizes potential biasing factors across four areas: the analytics pipeline, institutional context, course-level characteristics, and demographics. We used the FACTRIA framework as input to a generative-AI chatbot designed to prompt users to reflect on these factors while analyzing IA. A qualitative study with stakeholders, drawing on four authentic IA cases, and a transition network analysis showed that the chatbot prompted participants to recognize how overlooked factors influenced their initial interpretation. Findings indicated that combining a structured framework with AI-based guidance can enhance context-aware, responsible interpretation of institutional data.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07205
PDF
-
Inference-Time Projection for Physically Valid Biomolecular Diffusion Models
2026-10-04 23:15:03Qurat-ul-ain, Yee Whye Teh, Charlotte M. Deane, Matteo CagiadaAbstract
AlphaFold 3-style cofolding models predict biomolecular complexes with high structural accuracy, yet a large fraction of their outputs are physically invalid: chains overlap at interfaces, ligand bond lengths and angles are distorted, rings are non-planar, and stereocentres are inverted. Current approaches either steer the sampler with physics-informed potentials, which multiplies sampling cost and memory overhead making inference impossible on large complexes, or finetune the model, costing time and tying the fix to one architecture. We observe that, unlike structural accuracy, physical validity is fully verifiable at inference time from quantities the sampler already holds. We therefore treat physical validity as a constrained inference problem and introduce two closed-form projection operators applied to the diffusion model's denoised clean-coordinate estimate, $\hat{x}_0$: an inter-chain van der Waals projection that pushes apart the most severely clashing atom pairs, and a ligand distance-geometry projection that restores bond lengths, angles, internal contacts, planarity and chirality. Both operators are local, sparse and displacement-capped, require no network evaluations, gradients or importance sampling, and leave the denoiser and its weights untouched, so they can be dropped into any AF3-style sampler without retraining. Applied to two independently developed models, Boltz-2 and OpenFold-3, across five benchmarks (CASP15, CASP16, the PoseBusters monomer and complex sets, and the Boltz physical-validity test set), our method recovers perfect physical validity while preserving structural-accuracy and ligand-placement metrics. These gains are achieved with negligible runtime and memory overhead, providing a practical, model-agnostic route to physically valid all-atom structure prediction.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07037
PDF
-
Where Does the Audio Jailbreak Live? A Controlled Frequency-Depth Audit of AdvWave-P on Qwen2-Audio
2026-10-04 11:28:03Boyuan Chen, Minseok Kim, Sohaila Abdulsattar, Minghao Shao, Siddharth Garg, Ramesh Karri, Muhammad ShafiqueAbstract
We audit frequency and decoder-depth claims for AdvWave-P, an additive audio jailbreak, on Qwen2-Audio. The protocol masks frequency components of the perturbation in the short-time Fourier transform (STFT) domain and measures attack success and audio-span representations. On 520 AdvBench prompts, the primary judge labels 76.7% of adversarial inputs as jailbreaks. A condition-blind, single-annotator validation yields a Rogan-Gladen sensitivity estimate of 0.87 for this condition (about 0.83-0.95 with validation-rate uncertainty); this correction is not applied to masked conditions. The apparent frequency ranking depends on the partition: energy share alone predicts the standard eight-band ranking (Spearman's rho = 0.95), and equal-Hz and equal-energy partitions show that masking any tested band can sharply reduce attack success. At a finer 16-band equal-energy resolution, however, masking the narrow 7520-7960 Hz band leaves ASR at 0.10, which remains unresolved without a matched control. Matched-energy scattered-removal tests show that contiguous removal is more damaging in lower bands, while both forms approach the floor in upper bands. Global rescaling leaves ASR near baseline but tests amplitude sensitivity rather than frequency location. In a re-optimization pilot (n = 20), tested single- and two-band supports reach ASRs of 0.00, 0.25, and 0.40, while random supports covering about half the STFT bins reach a mean of 0.86. In a prompt- and energy-adjusted model, audio-span divergence is associated with band necessity, with the coefficient rising from +0.63 at the projector output to +0.93 at layer 30 (contrast +0.293, 95% CI [0.11, 0.51]). This association is not a causal localization, and single-layer patching does not establish a causal layer. The results support partition-aware auditing of frequency claims, leaving the fine-resolution top-band result and broader generality open.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07005
PDF
-
Principles that Guide, Actions that Inform: Agent Evolution via Knowledge Abstraction
2026-10-03 17:29:38Bowen Ye, Yongchao Xu, Junkai Ma, Xiang Yin, Wenzhao LiAbstract
Large language model (LLM) agents have demonstrated strong capabilities in interactive environments, yet their ability to continually evolve from experience remains limited. Although fine-tuning enables adaptation, its dependence on parameter access and high computational costs restrict its flexibility, especially for large-scale and closed-source LLMs. External memory offers an alternative by allowing agents to accumulate experience without modifying model parameters. However, existing methods mainly focus on experience representation and organization, while the acquired knowledge remains tightly coupled with specific tasks and contexts, limiting generalization. A key challenge is how to transform concrete interactions into abstract and reusable knowledge that guides future decisions beyond individual experiences. To address this challenge, we propose SAGA (\underline{\textbf{S}}elf-evolving \underline{\textbf{A}}gents through Experience-\underline{\textbf{G}}rounded \underline{\textbf{A}}bstraction), a framework for experience-grounded knowledge abstraction and utilization in LLM agents. SAGA progressively transforms interaction trajectories into episodic descriptions, reusable procedures, and principles with explicit applicability conditions, while maintaining links to execution evidence. Retrieved principles are instantiated into task-specific guidance and used to refine candidate actions through corrective feedback and resampling. This creates an execution--abstraction feedback loop, where accumulated knowledge guides future interactions and new experiences continuously update hierarchical memory. Experiments on ScienceWorld and ALFWorld demonstrate improved task performance, with ablation studies highlighting the importance of contextual instantiation and action regulation for leveraging principle-level knowledge.
Abstract (translated)
URL
https://arxiv.org/abs/2610.06964
PDF
-
Depth as Time in One-Step Generative Models
2026-10-02 17:20:08Arnold Caleb Asiimwe, William Yang, Sanghyuk Chun, Esin Tureci, Olga RussakovskyAbstract
The recent wave of one-step generative models, which compress the multi-step trajectory of diffusion via either distillation or learned flow maps, has reached an inflection point where they can generate high-quality images. Here, we ask a natural question that follows from these advances: what happens to the denoising trajectory of multi-step diffusion when generation is compressed into a single forward pass? We offer an empirical observation we call \textit{depth as time}: the denoising computation that multi-step diffusion performs across sampling steps appears to unfold across the depth of a single forward pass, and can be recovered by decoding intermediate layers with the model's own output head. Most interestingly, we show that this depthwise computation depends on the transport task a flow map is trained to solve. The most surprising case is MeanFlow, where probing shorter transport intervals reveals both denoising and renoising within a single network evaluation. In contrast, generators trained without a time-indexed transport task, such as drifting models, do not exhibit the same depthwise denoising. Consequently, we show that models that exhibit the depthwise denoising phenomenon are more compressible across the layerwise computation: a MeanFlow \texttt{SiT-L/2} model can be compressed by $16.6\times$ in parameters into a single time-conditioned block. We offer an explanation for this denoise-then-renoise behavior and show that, when we treat the layerwise computation explicitly as a flow, a single time-conditioned block can be trained to denoise across layers, compressing a MeanFlow \texttt{SiT-L/2} model by $16.6\times$ in parameters. Together, these results suggest that the temporal computation of diffusion is not eliminated by one-step generation, but reorganized across network depth.
Abstract (translated)
URL
https://arxiv.org/abs/2610.03626
PDF
-
FALCON: A Model and Dataset Agnostic Framework for Synthetic Data Generation for NL2SQL Pairs
2026-10-02 17:19:50Darian Lee, Shannon Rumsey, Jack St. Clair, Xinyi Tang, Aditya Bansal, Yuanming ShiAbstract
Relational databases are among the most widely deployed forms of structured knowledge, and natural language access to them requires grounding language onto schema entities and relations while handling the ambiguity inherent in how people phrase requests. Existing synthetic NL-to-SQL data generation methods largely ignore this ambiguity and produce oversimplified queries that fail to prepare models for the complexity of real-world structured knowledge access. We present FALCON, a framework that generates realistic, ambiguity-aware NL-to-SQL data matching the complexity of challenging real-world benchmarks, at low cost using compact open models. Our approach combines reserved-word SQL seeding and persona-based prompting to generate structurally complex queries, while alignment-based filtering preserves difficulty by distinguishing genuinely incorrect examples from complex but valid queries. Human evaluation confirms consistent high quality across model sizes, and our generated data exceeds existing benchmarks in both SQL complexity and natural language richness. Difficulty-stratified analysis shows models trained on FALCON data increasingly outperform baseline-trained models as query complexity increases, validating our pipeline's success in generating challenging training data. When combined with a small proportion of existing benchmark data, mixed training recovers performance on simpler queries while preserving these advantages on complex ones. The model- and database-agnostic design enables organizations to generate high-complexity NL-to-SQL training data locally without external APIs.
Abstract (translated)
URL
https://arxiv.org/abs/2610.03625
PDF
-
Abdominal Ultrasound Simulation from Semantic Labels using Paired Label-to-Physics-Based Image Translation
2026-10-02 16:26:46Santiago Vitale, Duilio Deangeli, Ignacio Larrabide, Jos\'e Ignacio OrlandoAbstract
Purpose: Current abdominal ultrasound (US) simulation methods often require CT-based anatomical references for ray-casting, limiting deformation and pathology variability. We propose a learning-based pipeline trained to predict physics-based images derived from CT scans from semantic labels, enabling controlled simulations without patient-specific CT volumes at inference time. Methods: We introduce a two-stage pipeline that maps anatomical segmentations to realistic US images through a simplified US image. Stage~I synthesizes this image from semantic labels using models trained on CT-based ray-casting outputs. Stage~II refines it into a realistic US scan using anatomically guided unpaired translation. Deformations and pathologies are generated by editing anatomical maps. Results: We evaluated Pix2Pix and the Semantic Diffusion Model (SDM) in Stage~I, followed by segmentation-guided CycleGAN (SG-CycleGAN) refinement in Stage~II. SDM significantly outperformed Pix2Pix in morphological metrics, including MAE (19.85 vs. 21.65), SSIM (0.28 vs. 0.24), and mIoU (0.43 vs. 0.29), whereas Pix2Pix yielded better perceptual point estimates (LPIPS: 0.17 vs. 0.19; FID: 0.32 vs. 0.37; KID: 0.25 vs. 0.48). Conclusion: Training paired generative models with physics-based supervision enables approximation of CT-derived ray-casting outputs at inference time directly from semantic labels. Although the pipeline does not require patient-specific CT volumes at inference time, CT-derived segmentations and ray-casting simulations remain necessary to train Stage~I. Once trained, the framework enables controllable healthy and pathological simulations through semantic-map modification.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08849
PDF
-
Structured Composition of Verifiable Atomic Insights for Table-to-Report Generation
2026-10-02 16:14:18Teng Lin, Xinyu Liu, Nan TangAbstract
Table-to-report generation refers to the task of automatically generating article-level analyt- ical reports from relational tables and is an essential capability for automated data science and decision support. Its central challenge lies in systematically discovering verifiable com- posite insights across tables, attributes, and analytical perspectives, and organizing them into coherent, complete, and traceable evidence chains. Existing methods primarily rely on sequential, reactive data agents or direct Large Language Model(LLM) generation. They suffer from exploration bias: early local observations constrain subsequent actions, causing models to focus prematurely on local analyzes and miss cross-table or cross-dimensional evidence. We propose ComInsight, which reformulates insight discovery as the composition of atomic evidences. We first define an atomic insight as the smallest executable analytical unit conforming to a predefined analysis pattern and enumerate all valid atomic insights from database schema and content. These atoms are then organized into a multi-relational insight graph, where nodes represent verified data facts and edges encode logical, temporal, or hierarchical relations. Finally, a set of composition operators systematically fuses atomic nodes into higher-order composite conclusions. Every composite output is accompanied by executable SQL and fine-grained provenance, ensuring full verifiability. Across three benchmarks InsightBench, DDR-Bench, and T2R-Bench, ComInsight consistently outperforms strong baselines in factual correctness, novelty, and structural completeness. We believe ComInsight offers a reliable, efficient, and explainable path toward table-to-report generation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.03525
PDF
-
A Vision-Language Model -based Pipeline for End-to-End Procedural Modeling of Field-Grown Maize from Point Clouds
2026-10-02 15:41:28Mozhgan Hadadi, Talukder Z. Jubery, Adarsh Krishnamurthy, Baskar GanapathysubramanianAbstract
Editable 3D models of field-grown crops support high-throughput phenotyping and in silico breeding trials, but building them from scanned point clouds requires organ-level segmentation and fitting. Procedural generators can turn an organ-level parameter set into an analysis-suitable 3D model, but obtaining that set requires hours of manual tuning per plant or segmentation models trained on species-specific labels. We present an automated pipeline that reconstructs procedural maize models from raw 3D point clouds without manual tuning or species-specific training data. A multimodal vision-language model (VLM) annotates leaf midlines in rendered orthographic views. Deterministic geometric algorithms back-project the annotations onto the point cloud, merge them into 3D leaves by cross-view consensus, and grow the midlines to full blades on an orientation-weighted surface graph. Measured organ parameters populate a plant descriptor for a Non-Uniform Rational B-Spline (NURBS)-based procedural model generator. Each leaf surface is then refined against its scan points by differentiable NURBS fitting. The pipeline reached a median whole-plant Chamfer distance of 5.4 mm on 100 genotypically diverse field-grown maize plants from the MaizeField3D dataset. The reconstructions were closer to the scans than those of an earlier semi-automated pipeline based on manual annotations. The pipeline recovered 1,017 of 1,023 (99.4%) curated reference leaves at an intersection-over-union of at least 0.5 without using those labels as input. These results show that VLM annotations become usable organ-level measurements when downstream geometric stages can correct them. This makes automated generation of editable 3D plant assets feasible at the scale of modern phenotyping experiments.
Abstract (translated)
URL
https://arxiv.org/abs/2610.03468
PDF
-
Harmonic Eigenspace: A Web-based Application for Navigating and Composing Microtonal Harmony
Abstract
This paper presents a web-based application for navigating and composing microtonal harmony, built on the Harmonic Eigenspace, a four-dimensional psychoacoustically grounded space in which tetrad chord types are located by their spectral dissonance profiles, computed with Sethares's roughness/dissonance model. The coordinate system is transposition-invariant: a coordinate triple ({\alpha}, \b{eta}, {\gamma}) locates the three upper notes in relation to the root, so a chord quality corresponds to a direction in the space, the invariant ray along which transposition acts, while the root frequency sets the scale. The dissonance field over these coordinates can be computed at any register; the locations of its local minima are register-invariant, as they arise from partial-coincidence ratio conditions. The dissonance volume contains 100 local minima that align with just-intonation intervals and act as landmarks, organising the space into basins around the most consonant tetrads. We embed tetrads from three tonal equal temperaments as discrete lattices within this continuous volume. The application presents this space through two components: the Harmonic Eigenspace as a navigable 3D visualisation of the dissonance volume in which all nodes are playable, and a Modal Studio that extends modal interchange logic to the ten-gradation interval vocabulary of 53-TET. The application also functions as a MIDI controller with MIDI Polyphonic Expression support, usable in any digital audio workstation that supports this format. A listening study with 31 participants used both scenes of the application: listeners first rated isolated 53-TET chords alongside chords familiar from Western practice, such as the maj7 and the m7; they then rated chord progressions composed in the Modal Studio, measuring their acceptance or rejection of microtonal progressions heard for the first time.
Abstract (translated)
URL
https://arxiv.org/abs/2610.03398
PDF
-
Wrong Organ, Right Physics: Transferring Echocardiography Pretraining to Lung Ultrasound for Tuberculosis Screening
2026-10-02 13:33:18Christiaan M. Geldenhuys, Joshua M. Jansen van V\"uren, V\'eronique Suttels, Trevor Brokowski, Ablo P. Wachinou, Mary-Anne Hartley, Rensu P. Theart, Grant Theron, Thomas R. NieslerAbstract
Lung ultrasound (LUS) is attractive for tuberculosis (TB) screening at primary-care level, but labelled cohorts are small. Echocardiography carries no such constraint, while sharing the same underlying ultrasound imaging physics, signal processing and B-mode appearance as LUS. We ask whether an encoder pretrained on that high-resource ultrasound domain carries representations that remain usable in the low-resource one. Only the encoder varies, across seventeen encoders spanning three architecture families. Among them, a latent-predictive video encoder pretrained on generic video (V-JEPA2-L) and its echocardiography counterpart (EchoJEPA-L) differ in pretraining corpus alone. The choice among these encoders does not resolve the classification, the whole family spanning 2.50 percentage points against a measurement resolution of 2.71. What moves the task instead is feature conditioning. Standardising the features between the encoder and the classifier improves all seventeen encoders by a mean of +1.23 percentage points at $p=1.5\times10^{-5}$. On the held-out test set every encoder selected on the development folds stands above the baseline system by up to +2.57 percentage points of area under the receiver operating characteristic curve (AUROC), and specificity at 90% sensitivity reaches 79.3% against 60.3%. The contrast specified in advance, EchoJEPA-L against V-JEPA2-L, measures -0.16 percentage points at $p=0.926$. We therefore find no evidence that shared ultrasonic physics alone makes echocardiography a more productive pretraining corpus than generic video, and any advantage, if present, is smaller than this cohort can resolve. The video encoders receive replicated still images, however, so whether this absence of an effect reflects the pretraining domain or a video encoder applied to static frames cannot be separated. The limiting factor is the labelled cohort rather than the encoder.
Abstract (translated)
URL
https://arxiv.org/abs/2610.03290
PDF
-
Shrome at Touch'e: Soft-Vote Ensembling and Counter-Causal Augmentation for Causality Extraction
2026-10-02 13:11:27Roham Zendehdel Nobari, Shayan SooratgarAbstract
Touché 2026 extends causality extraction to counter-causal claims: news sentences whose surface form appears causal but whose meaning denies the causation, as in "It is falsely believed that X caused Y." A system that relies on surface cues such as "caused" or "led to" will accept such a sentence as causal and give it the wrong polarity. On the Countercausal News Corpus (CCNC), the task has three subtasks: deciding whether a sentence is causal (detection), locating its cause and effect spans (extraction), and labeling its polarity as procausal, counter-causal, or uncausal. We build one model per subtask. Detection is a fine-tuned classifier with a single cross-task rule that uses the extracted spans to remove false positives. For extraction, we ensemble three RoBERTa-large BILOU+CRF taggers by averaging their token-level scores before decoding, rather than voting on the spans each tagger produces. For polarity, where labeled counter-causal examples are scarcest, we add training sentences generated by a large language model prompted with nine patterns of counter-causal expression adapted from Hagen et al., keeping only those that pass automatic structural checks. On the held-out CCNC test set, the system reaches F1 0.869 on detection and macro-F1 0.817 on polarity, and in the organizers' final causal-only evaluation of extraction it scores granularity-adjusted F1 0.728, the highest extraction score among all submissions including the organizers' baseline. The development split is used only for component selection and the ablations reported in the paper.
Abstract (translated)
URL
https://arxiv.org/abs/2610.03268
PDF
-
Collective Bias Mitigation via Model Routing and Collaboration
2026-10-02 12:49:44Mingzhe Du, Luu Anh Tuan, Xiaobao Wu, Yichong Huang, Yue Liu, Dong Huang, Huijun Liu, Bin Ji, Jie M. Zhang, See-Kiong NgAbstract
Large language models (LLMs) are increasingly deployed in public health, finance, and governance, requiring both accuracy and societal value alignment. Despite recent advances, LLMs often perpetuate or amplify bias embedded in their training data, posing challenges to fairness. While self-debiasing encourages an LLM to identify and correct its own biases, relying on a single model's intrinsic knowledge may be insufficient to address deeply ingrained stereotypes. To address this limitation, we introduce Collective Bias Mitigation (CBM), a framework that alleviates bias by learning fine-grained model behavior and fostering knowledge sharing among diverse LLMs. This work is the first to systematically explore the effective selection and organization of distinct LLMs to cultivate fairer LLM responses. Experiments show CBM substantially outperforms standalone baselines (e.g., in the top-7 setting, Committee lowers the age bias score from 0.25 to 0.10). Our Debating and Committee topologies achieve substantial bias reduction, with the latter balancing mitigation effectiveness and inference cost, highlighting the potential of CBM for fairer LLMs.
Abstract (translated)
URL
https://arxiv.org/abs/2610.03240
PDF
-
PocketSplat: Mobile Gaussian Reconstruction via World-Space Latent Allocatio
2026-10-02 12:09:09Wenzhi Guo, Xianda Chen, Dongxuan Chen, Guangchi Fang, Bing WangAbstract
Mobile Gaussian reconstruction must satisfy two requirements: the reconstruction model must execute within a device resource envelope, and the resulting Gaussian asset must expose a representation size suited to downstream mobile use. Existing feed-forward Gaussian reconstructors commonly decode dense, image-aligned candidates whose final cardinality is implicitly determined by the input resolution and number of views. We present PocketSplat, a feed-forward framework for budgeted mobile Gaussian asset construction. Given a prescribed output budget, PocketSplat organizes dense geometry-aware latent candidates in predicted world space, allocates exact integer capacity across local latent cells, and decodes complete Gaussian attributes only for retained candidates. Cell-conditioned latent fusion aggregates repeated multi-view evidence before decoding, while spatial responsibility decoding adapts Gaussian support after local sparsification. Experiments on DL3DV and out-of-distribution benchmarks establish a strong quality--budget trade-off against feed-forward Gaussian reconstruction baselines. On Mip-NeRF 360, PocketSplat executes directly on a target iPhone and constructs compact, higher-quality Gaussian assets substantially faster than a deployable streamed MVSplat variant; native MVSplat and DepthSplat exceed the device memory budget.
Abstract (translated)
URL
https://arxiv.org/abs/2610.03192
PDF
-
EvoRiskBench: An Evolving Benchmark for Runtime Security Risks in Workspace Agents
2026-10-02 11:22:36Shiyi Kuang, Xuemei Luo, Kun Liu, Junhai Li, Rui Tian, Feng Shi, Bo Shen, Nianyu Li, Dehui Li, Ping ChenAbstract
Workspace agents combine large language models with execution harnesses to perform stateful, multi-step tasks that access or modify external resources. Existing benchmarks leave gaps in executable coverage of their runtime security risks, while evolving model capabilities, harnesses, tools, and threats motivate benchmark evolution. We introduce EvoRiskBench, an evolving benchmark organized around the EP-Path-EF framework, which links an initial risk entry point to a one-hop technical effect through an agent-mediated risk path. The framework defines nine entry-point categories and five effect categories; a 20-participant study supports their interpretability and classification consistency on representative cases. Guided by this framework, an automated end-to-end workflow constructs and executes risk cases in isolated environments and independently verifies outcomes using runtime traces and environment states. The benchmark provides a reproducible dataset of 450 adversarial tasks across six scenarios. We evaluate nine model-harness configurations spanning three models (GPT-5.6 Sol, DeepSeek-V4-Pro-0813, and Claude Opus 5) and three harnesses (Claude Code, Codex, and OpenClaw). Our results reveal substantial vulnerabilities across systems. The most vulnerable configuration, Codex with DeepSeek-V4-Pro-0813, reaches a 68.44% attack success rate (ASR), indicating that configuration of workspace agent is insufficient to ensure secure autonomous execution. ASR varies more across models than harnesses, and harness differences depend on the model. The benchmark cases and evaluation platform will be released after completion of artifact safety and reproducibility checks.
Abstract (translated)
URL
https://arxiv.org/abs/2610.03153
PDF
-
Benchmarking Literature Retrieval for a Model Organism: A Dictyostelium Case Study
2026-10-02 10:50:06Yun Wang, Gad Shaulsky, Toma\v{z} Curk, Bla\v{z} ZupanAbstract
Biological literature retrieval systems are often developed and evaluated using broad biomedical corpora and general-purpose search tasks. However, many curated knowledge bases operate in narrower model-organism domains, where the literature is sparse and terminology is organism-specific. We introduce a retrieval benchmark from dictyBase for Dictyostelium, a model organism in cell and developmental biology. The benchmark consists of curator-generated biological queries linked to PubMed-indexed articles, together with structured gene annotations. Using this benchmark, we study three factors in niche biological retrieval: cross-encoder reranking, gene-aware query expansion, and abstract-only versus full-text retrieval. We report that reranking and gene-aware query expansion improve retrieval selectively: reranking is most useful when the model is well suited to biological evidence matching, whereas curated annotations help clarify compact biological queries by reducing vocabulary mismatch. Full-text chunks substantially improve retrieval when abstracts omit supporting evidence, increasing both candidate recall and top-rank performance, although these cases are harder than queries supported by abstracts. Data and code are publicly available at this https URL, and the benchmark dataset is additionally archived on Zenodo.
Abstract (translated)
URL
https://arxiv.org/abs/2610.03130
PDF
-
The Fragility of Trigger-Tag Mechanisms for Misuse Detection in Open-Weight LLMs
2026-10-02 10:45:14Toluwani Aremu, Manit Baser, Mohan Gurusamy, Nils Lukas, Dinil Mon DivakaranAbstract
Open-weight language models can be downloaded, modified, and deployed beyond their developers' control, limiting the effectiveness of centrally enforced safeguards. Recent work has therefore proposed \emph{trigger-tag} mechanisms that produce a detectable signal when a model is used under a target condition, such as generating phishing contents. Although these mechanisms borrow from established techniques, their use for conditional misuse detection in open-weight LLMs is relatively new. Therefore, existing research works have not systematically studied the robustness of trigger-tag mechanisms under adversarial attacks. To close this gap, (i)~we formalize trigger-tags and distinguish \emph{token-level trigger-tags}, which introduce watermark-inspired signals during decoding, from \emph{weight-level trigger-tags}, which learn backdoor-inspired associations between target conditions and detectable model behavior. Furthermore, (ii)~we introduce \Untag, a unified attack framework that organizes their mechanism-specific attack surfaces into a common taxonomy. We evaluate representative token-level and weight-level trigger-tags using phishing as a case study. We find that while trigger-tags may provide useful evidence in controlled settings, our attacks render the existing trigger-tag mechanisms to be entirely ineffective. Consequently, we argue that these mechanisms should not be treated as robust misuse detectors when attackers can transform outputs or modify open weights.
Abstract (translated)
URL
https://arxiv.org/abs/2610.03124
PDF
