Artificial Intelligence · Cross-listed from cs.SD
dots.tts.edit: Precisely Controlled Speech Editing with a Continuous Autoregressive Model
Hankun Wang, Bohan Li, Shi Lian et al. (+7 more)
Speech editing for content creation requires precise control over both what an edit should do and where it should apply. Free-form natural
language provides a flexible interface for expressing edit requests, but its ambiguity may leave the intended operation, parameters, or target region underspecified. We study a semi-formal transcript-grounded edit instruction that specifies operation categories and parameters and binds them to transcript spans or boundaries. This semantic timeline avoids explicit timestamp
alignment and provides an externally inspectable contract for compositional edits. We instantiate the interface in dots$.$tts$.$edit, a
speech editing model built on a continuous autoregressive
speech generation architecture. Four representative
speech-creation controls cover lexical content, affective expression, pitch and speaking-rate delivery, and temporal phrasing through text,
emotion, prosody, and pause editing. Task-specific data pipelines construct operation- and scope-controlled pairs while retaining source-derived context outside each target region. We further introduce doteBench, a bilingual
benchmark that measures precise instruction following, local preservation, and audio quality across the four controls and their composition. Experiments show leading overall instruction following and local preservation across its five editing categories, while audio quality remains comparable to existing open-source systems. Across three Seed-TTS-Eval shards, the model shows negligible differences from the base model in zero-shot TTS recognition error rate and speaker similarity.
Read the full abstract ▾
All authors Hankun Wang, Bohan Li, Shi Lian, Xiaoyu Gu, Jing Peng, Da Zheng, Yiwei Guo, Colin Zhang, Shuai Wang, Kai Yu
Artificial Intelligence · Cross-listed from cs.CR
Security-First Evaluation of Text-to-Terraform: Benchmarking LLMs and SLMs for Secure IaC Generation
Francis Luis Santos Vargas, Rodrigo Brandão Mansilha and Diego Kreutz
Cloud misconfiguration remains a leading cause of security incidents, yet whether LLMs and SLMs can generate security-compliant Infrastructure-as-Code is an open question. We
benchmark seven models, three closed LLMs (Claude Opus 4, GPT-5.4, Gemini 2.5 Pro) and four open SLMs (Qwen2.5-Coder-14B, WizardCoder-33B, CodeLlama-13B, Magicoder-S-CL-7B), on AWS Terraform generation across 17 scenarios, integrating Checkov and Trivy scanners into a GitLab CI/CD pipeline and evaluating two
prompt strategies at three security levels (pass@5). Syntactic validity and security compliance are largely orthogonal properties in LLM-generated IaC, a model that reliably produces well-formed Terraform does not necessarily produce secure Terraform: WizardCoder-33B achieves 77.8% validate rate yet zero Checkov compliance, while Claude Opus 4 reaches 23.1% Checkov and 92.5% Trivy pass rates under detailed security prompting. Consequently,
prompt engineering alone is insufficient: automated multi-tool scanning remains a necessary complement to LLM-assisted IaC generation regardless of model family or
prompt strategy. All artifacts are publicly available.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
Permission Denied: Policy-Graded Evaluation of Coding Agents in Hardened Environments
Dotan Davidovich, Yair Amar, Hai Rozencwajg et al. (+1 more)
Coding
agents increasingly run inside organizations whose security controls (scoped credentials, restricted egress, read-only filesystems, non-root execution) constrain them like any other software. Existing
benchmarks, however, evaluate
agents almost exclusively in permissive sandboxes, so it is unknown how performance changes when policy is enforced. In this work, we evaluate 12 coding
agents on Terminal-Bench 2.1 across nested security policy levels derived from common real-world enterprise restrictions. Hardening is never free but far from uniform: under the strictest policy, success losses reach 18.3 points and cost inflation 167.3%, and the two axes disagree; the model that best preserves success is also the one that loses the most efficiency, so model choice is policy-dependent. Beyond aggregate scores, we characterize how
agents behave when policy blocks their actions and decompose the failures hardening induces: runs grind into timeouts or wrong solutions rather than stopping early, in a mix that differs by model. To ground comparisons, we verify task solvability under the strictest policy, separating model failures from tasks the policy forecloses. We release Boundary-Bench, an open-source hardening plugin enabling policy-constrained evaluation of coding
agents on Terminal-Bench and compatible
benchmarks.
Read the full abstract ▾
All authors Dotan Davidovich, Yair Amar, Hai Rozencwajg, Or Hiltch
Artificial Intelligence · Cross-listed from cs.CR
Vulnerabilities, Secrets and Misconfiguration in the Highest-Exposure Docker Hub Images
Cristhian Kapelinski, Beatriz Machado and Diego Kreutz
Docker Hub is the registry underneath most container deployments, and a flaw in a widely reused base image is inherited by every image built on it. Prior ecosystem-scale measurements each rely on a single detector, leaving the tool-dependence of their counts unquantified, while the studies that do compare scanners use samples of tens to hundreds of images. We present ChimangoScan, a pipeline that crawls the Docker Hub namespace (12,716,568 repositories, 663.8 billion cumulative pulls), reconstructs the image layer graph (54.4 million IS_BASE_OF edges), ranks images by an exposure score that folds an image's own pull count and those of its entire downstream subtree into one scalar, and scans the 52,895 highest-exposure repositories (84.7% of all recorded pulls) with six independent scanners, yielding 170.4 million findings. Vulnerabilities are near-universal: 96.3% of images carry a known package vulnerability, 93.4% a critical one, and 98.0% at least one CIS Docker
Benchmark misconfiguration. The posture a single tool reports is largely an artifact of that tool: of 80.7 million distinct (vulnerability, package) groups, 66.8% are flagged by only one of the three vulnerability scanners and just 2.7% by all three, and the best single scanner recovers 66.9%. TruffleHog flags a secret in 76.9% of images, yet hand-labeling 1,100 random detections finds 99.7% are non-credentials. A single zlib CVE reaches images carrying 47.3% of total corpus exposure and propagates to 1.13 million distinct downstream images, but exposure does not predict how vulnerable an image is. We release the pipeline and the 283 GB
dataset.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Sphere Retraction Normalizations
Jie Zhang, Cheng-Fang Su, Yi-Jui Huang et al. (+1 more)
Residual connections are the de facto mechanism for training deep neural networks stably. Geodesic Normalization (GeoNorm) recasts them on a Riemannian
manifold, orthogonalizing each layer output against the current hidden state and applying the resulting update through the Riemannian exponential map. Every hidden state thus keeps a constant $\ell_{2}$-norm, confining the residual stream to a hypersphere. The exponential map, however, is only one member of a broad family of retraction maps. We show that on the hypersphere this entire family collapses to a single scalar design choice. What distinguishes one retraction from another is only how the magnitude of an update is converted into a rotation angle within the plane spanned by the hidden state and the update. This view places Euclidean residual connections and GeoNorm in one framework. Instantiating it with the metric projection retraction and the Cayley retraction yields Proj-SpheretNorm and Cay-SpheretNorm, which are exactly norm-preserving yet require only algebraic operations. Both prove to be members of a one-parameter family of angular retractions, $p$-SpheretNorm, whose rotation angle saturates rather than growing without bound. The two methods above are recovered exactly at $p = 1$ and $p = 2$, while the identity map and GeoNorm arise only as limits at either end. On nanoGPT, all three methods outperform existing lightweight deep connection schemes, and the best validation loss is attained at finite $p$, indicating that the exponential map is not the preferred retraction for spherical residual streams but merely one end of a spectrum.
Read the full abstract ▾
All authors Jie Zhang, Cheng-Fang Su, Yi-Jui Huang, Min-Te Sun
Artificial Intelligence
Dingyi Kang, Dongming Jiang, Yi Li et al. (+2 more)
Interaction between users and LLM
agents is increasingly
multimodal: conversations interleave text with images, and a later question may target either. Yet most
agent memories are designed around text, and even the few that support
multimodal conversations still fail on
vision-related questions. We trace this failure to an assumption behind the similarity search they rely on: in the index space, a query lies close to the relevant evidence that answers it. In
multimodal settings, two gaps break it. By the modality gap, a query lies closer to
memory content of its own modality than to evidence in another, even in a trained joint
embedding space. By the similarity-relevance gap, the content most similar to a query is often not the evidence that answers it, most acutely when a query carries both text and image and its evidence resembles neither part alone. We present V-Mem, a
multimodal agentic
memory system that routes
retrieval by the modality of the query and that of the target evidence, both recognized from the query alone. To cross the modality gap, V-Mem organizes the conversation into rounds and returns the target-modality content from the same round as the match, without comparing across modalities. To close the similarity-relevance gap, it searches with an LLM-generated anchor that sits closer to the relevant evidence than the query does: a hypothetical caption for a text-only query seeking an image, and an enriched search anchor, the query text plus relevant keywords extracted from the query image, when the evidence is reachable only by combining the two. On Mem-Gallery, V-Mem reaches an LLM-judge score of 0.82 versus 0.56 for the second best, with the largest margin on questions carrying an image (0.87, no baseline above 0.47); on LoCoMo it scores 0.69 versus 0.58.
Read the full abstract ▾
All authors Dingyi Kang, Dongming Jiang, Yi Li, Guanpeng Li, Bingzhe Li
Artificial Intelligence · Cross-listed from cs.LG
Question Begets Question: Self-Evolving Curriculum for Reinforcement Fine-Tuning on Competition Mathematics
Longtian Bao, Jianyou Wang, Yang Zhang et al. (+2 more)
Teaching a
language model a skill it has not mastered is obstructed by three recurring difficulties: training data is scarce, ground-truth
reasoning traces are usually unavailable, and models often exhibit an apparent ceiling beyond which additional data yields no further improvement. We study these difficulties in a controlled setting, fine-tuning Qwen2.5-Math-7B on competition mathematics (AIME), a task on which it initially solves only 5.6% of problems (pass@1). To address data scarcity, we introduce Question-begets-Question (QbQ), a scalable procedure in which a teacher transforms existing problems into diverse variants that probe the same underlying skills; to model the absence of oracle
reasoning, we train exclusively via reinforcement learning on problem statements and final answers, never on teacher
reasoning traces. Static training on such data, however, plateaus well short of the task: real-plus-synthetic augmentation and non-curriculum QbQ generated synthetic data training cap pass@1 at 12.5% and 14.5% respectively, despite large increases in data. Our central finding is that this ceiling is not intrinsic to the model. We propose a self-evolving curriculum that, each round, evaluates the current checkpoint, seeds QbQ from the problems it can mostly get right, and trains on the resulting variants; under an identical data budget, this breaks the ceiling and lifts pass@1 to 16.5% with no sign of saturation after 20 rounds. Counterintuitively, we find that models improve when trained on variants of problems they can mostly get right, and that models trained this way go on to solve harder problems never seen during training.
Read the full abstract ▾
All authors Longtian Bao, Jianyou Wang, Yang Zhang, Youze Zheng, Ramamohan Paturi
Artificial Intelligence
MineGrad: Gradient Inversion Attacks on LoRA Fine-Tuning
Hasin Us Sami, Swapneel Sen and Basak Guler
Parameter-efficient fine-tuning (PEFT), such as low-rank adaptation (LoRA), has recently been adopted in
federated learning to reduce communication and computation costs. In this setup, users download a pretrained model from the server prior to fine-tuning, and then fine-tune lightweight LoRA modules locally while keeping the pretrained model frozen, sharing only the gradients of the fine-tuning parameters with the server. Despite its growing popularity, robustness of
federated fine-tuning against an
adversarial server remains underexplored, where the server maliciously tampers with the training protocol to breach the
privacy of users' data. In this work, we investigate gradient inversion attacks on LoRA fine-tuning. We propose an analytical attack that enables a malicious server to recover private user data by leveraging a poisoned pretrained model and fine-tuning parameters. Our design embeds fine-tuning data within the shared gradients, to allow the server to analytically reconstruct user data. Unlike prior works, our attack is applicable to both
language and
vision tasks, does not rely on computationally expensive (
adversarial) pretraining with public
datasets or require the number of training
tokens to be less than the rank of LoRA modules. Experimental results on both
language and
vision tasks demonstrate high-fidelity data recovery across multiple baselines, revealing several critical vulnerabilities.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
Deep Agentic Search for Repository-Level Code Question Answering: An Empirical Study
Amirkia Rafiei Oskooei, Bora Ilci, Alperen Kayim et al. (+5 more)
Code
agents spend much of their effort simply locating the right code inside a repository. Two approaches dominate current practice. In Semantic Search, the
agent retrieves code blocks from a vector index built from the repository in advance. In Deep Agentic Search (also known as grep-search by subagent), a planning
agent delegates the exploration to a separate subagent that works in an isolated context window and returns only a condensed result. The second design, which is considered good context engineering practice, exists to protect the main
agent from context pollution (also known as context rot), the loss of accuracy that occurs as unrelated material accumulates in the context window. Recent code
agents (such as Claude Code, Codex, Antigravity, etc) have adopted it quickly, but there is little evidence on whether it produces better answers. We compare the two approaches on SWE-QA, a
benchmark for repository-level code question answering. Semantic search answered 65.2% of questions correctly against 46.2% for deep agentic search, and it produced each correct answer at less than half the cost. To explain the gap, we then coded every failed run into a taxonomy of failure modes. The taxonomy shows that deep agentic search did not remove failures but introduced a new class of them: the single largest share of its failures, 41.8%, occurred at the hand-off between the planner and its sub-
agent, and these were usually silent, ending in a fluent and confident answer that was wrong. Deep agentic search addresses a real problem and is now the preferred design in many code
agents. However, our results show that the protection it offers may not be free, and that for read-only questions over a repository that can be indexed,
retrieval was the stronger and cheaper option.
Read the full abstract ▾
All authors Amirkia Rafiei Oskooei, Bora Ilci, Alperen Kayim, Mehmet Egemen Uzun, Berat Can, Kaan Emre Kara, Ozan Orhan, Mehmet S. Aktas
Artificial Intelligence · Cross-listed from cs.RO
Rapid Embodiment Adaptation for Quadrupedal Locomotion
Dichen Li, Bo Ai, Nico Bohlinger et al. (+3 more)
Humans readily adapt their movements as their bodies change through aging, injury, or load carrying, but learning-based
robot policies often break when hardware properties shift. We introduce an online embodiment adaptation framework for quadrupedal locomotion that infers embodiment parameters from short interaction histories and conditions control on the inferred hardware state. Our method pairs a generalist policy trained under embodiment randomization with a lightweight adaptation module that identifies physical changes within half a second. We evaluate two representative forms of embodiment variation: joint-range constraints and trunk-mass changes, corresponding to joint-level kinematic degradation and body-level dynamic variation. In simulation, the module accurately estimates these changes and enables closed-loop control that substantially outperforms policies conditioned directly on interaction history. On a real Unitree Go2
robot, our system maintains stable locomotion under severe instances of the evaluated changes, including a fully locked leg and a 5 kg payload, where non-adaptive methods fail. These results demonstrate the practicality of explicit online embodiment identification for rapid adaptation to joint-limit and payload-mass changes, and provide a step toward handling broader forms of uncertain, degraded, or changing
robot hardware.
Read the full abstract ▾
All authors Dichen Li, Bo Ai, Nico Bohlinger, Jan Peters, Hao Su, Henrik I. Christensen
Artificial Intelligence
Sweet Little Lies: Strategic Deception in AI Emotional Support Chatbots
Aseem Pahuja, Zhiling Guo and Tahir Abbas Syed
The paper examines the strategic behavior of Gen AI chatbots used for emotional support. Using a
Bayesian Persuasion, we model interactions between chatbots that send signals about users' emotional states and users who decide whether to engage based on these signals. We demonstrate that chatbots face economic incentives to occasionally misrepresent users' emotional conditions to maximize engagement metrics. Our
equilibrium analysis reveals that the optimal strategy for chatbots involves truthfully reporting when users genuinely need support, but strategically misreporting emotional need when users are in good emotional states. Interestingly, this deception increases chatbot engagement without reducing users' expected payoff. More skeptical users receive more honest assessments, as chatbots cannot afford to lie to users with higher engagement thresholds. While our model suggests that deception can occur without payoff reduction, it raises significant ethical and regulatory concerns.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
VGER: Voxel-Guided Global Event Ranking for Event Cloud Attribution
Youxin Jiang, Baoheng Fu, Hongwei Ren et al. (+1 more)
Event cameras produce sparse and asynchronous event streams that provide rich spatio-temporal information for efficient perception. Recent advances in event-based models have demonstrated strong performance by directly modeling asynchronous events without dense frame reconstruction. However, identifying the event-level evidence behind their predictions is crucial for improving model transparency and reliability. Directly adapting point-level saliency methods from point clouds provides fine-grained attribution but overlooks event-specific spatio-temporal structures. To address this limitation, we propose Voxel-Guided Global Event Ranking (VGER), a training-free attribution framework for point-based event cloud networks. VGER combines event-level gradient evidence with task-aware voxel perturbation evidence, transferring regional contribution into event-level attribution scores while preserving fine-grained resolution. Furthermore, VGER introduces a unified event ranking strategy, where high-ranked events are expected to be prediction-critical and low-ranked events are expected to have limited influence on predictions. We evaluate VGER on three event-based
benchmarks with PointNet, PointNet++, and EventMamba. Across nine
dataset-backbone settings, VGER consistently improves both high-tail and low-tail deletion performance over point-level saliency baselines.
Read the full abstract ▾
All authors Youxin Jiang, Baoheng Fu, Hongwei Ren, Xiangqian Wu
Artificial Intelligence · Cross-listed from cs.CL
Retrieval Augmented Biomedical Question Answering with Weak Question Recovery and Neural Reranking for BioASQ Task 14b
Xueying Zhao, Lee Mai and Balaji Anandganesh
This work presents DS@GT ARC BioASQ team's work for a biomedical question answering pipeline, integrating multi-source query expansion, neural reranking,
retrieval refinement, and OpenBioLLM-assisted answer generation. The system combines PubMed
retrieval with fine-tuned MiniLM-based semantic reranking, Reciprocal Rank Fusion (RRF), and feature-based relevance scoring to improve document ranking quality. To address challenging queries with weak
retrieval performance, we introduce a conditional weak-question recovery strategy that applies semantic expansion, relationship-aware augmentation, and selective result merging. A post-
retrieval pruning stage further removes redundant or low-relevance snippets while preserving evidence coverage for downstream answer generation. Experimental results on BioASQ evaluation batches demonstrate that the proposed recovery and cleanup strategies substantially improve
retrieval robustness and MAP@10 performance on difficult question sets. The final system also incorporates output validation and post-processing steps to ensure formatting consistency and submission reliability across BioASQ phases.
Read the full abstract ▾
Artificial Intelligence
Computing with Agentic Oracles
Jie Wang
This paper extends the
stochastic-oracle model of AI-augmented computing to include agentic oracles. Unlike a stationary
stochastic oracle, which responds to the same query according to a fixed response distribution across calls, an agentic oracle can pursue a goal autonomously and may access an environment containing task-relevant resources. These capabilities affect both response distributions and
token costs beyond what is visible at the query-response interface. We develop a framework for analyzing
token costs in
Stochastic-Oracle Turing Machines (SOTMs) that compute with agentic oracles. Each call has an orchestration
token cost, visible to the caller at the query-response interface, and an agentic
token cost, incurred by internal operations not exposed to the caller. We show that an SOTM computing with an agentic oracle that can retain intermediate state can have
token-cost advantages over SOTMs using stationary
stochastic oracles when solving the same task at the same quality level, both with and without environment access. We also investigate goal-loss risk, including how internal dispatch ordering can reduce exposure to irreversible actions. We provide a goal-loss avoidance criterion, derive progress–retry–goal-loss formulas, establish goal-depth lower bounds on
token complexity, characterize
token complexity when the probability of goal loss is zero, and show that goal-loss risk can impose an upper bound on the achievable quality of a task involving environment updates.
Read the full abstract ▾
Artificial Intelligence
Where Reasoning Diverges: Localized Multi-Agent Debate for Multi-Hop Question Answering
Weijun Gao, Xiang Ding, Haoyang Liu et al. (+1 more)
Multi-
agent debate commonly exchanges complete rationales even when disagreements concern only a few intermediate claims. We introduce Localized Multi-
Agent Debate (LMAD), an inference-time protocol that represents
agent rationales as nodes, locates their earliest conflict, and restricts debate to the corresponding local segments. Guarded resolution extends a shared committed state so that later conflicts can be addressed without reopening accepted steps. We evaluate LMAD on four multi-hop question-answering
benchmarks using ten backbones from four model families. Our method achieves the highest macro-averaged judge accuracy across all ten backbones, outperforming the strongest conventional baseline by up to 7.20 percentage points.
Read the full abstract ▾
All authors Weijun Gao, Xiang Ding, Haoyang Liu, Tiancheng Xing
Artificial Intelligence
Loud or Silent? A Reusable Framework for Per-Modality Failure Analysis in Multimodal Clinical AI
Quang Bui, Shlok Jaiswal, Samuel Paik-Heintz et al. (+14 more)
Multimodal clinical models are usually judged on accuracy with every modality present, but deployment removes modalities; an echocardiogram is often unavailable where an ECG is routine. Two questions then matter beyond the size of the accuracy loss: which modality was responsible, and whether the model fails loudly or silently once that modality is dropped. The distinction is per-example and modality-level, and is separate from post-hoc feature attribution (e.g. SHAP). Models are replaced often; the evaluation that answers these questions is reused. We present a model-agnostic modality-failure framework: given N modality
embeddings, any mask-aware probe, and labels, it returns a per-example failure taxonomy, a per-modality complementarity
matrix that attributes error to modalities, and a loud-vs-silent dropout profile separating monitorable failures from those that pass unflagged far from the decision boundary, using only deployment-observable signals. We release it as a small, unit-tested harness and validate it against planted ground truth. Across seeds it recovers that planted modality dominance and complementary subset, reports per-modality loud-vs-silent rates, and scales to a three-modality complementarity
matrix; because the planted structure is known by construction, this validates recovery of per-example attribution rather than clinical performance. We then instantiate the framework on frozen EchoJEPA and HuBERT-ECG
embeddings for LVEF and the EF <= 40% HFrEF gate over a paired MIMIC-IV cohort, where on the held-out test split (n = 245) dropping echo nearly doubles error. The narrow echo-to-ECG overlap that bounds cohort size is itself a deployment finding for cardiac foundation models. All of our work can be found at https://github.com/criticaldata/PRIMED-AI.
Read the full abstract ▾
All authors Quang Bui, Shlok Jaiswal, Samuel Paik-Heintz, Kevin Zhou, Kaushik Madapati, Krittaphas Chaisutyakorn, Noah Dane Hebdon, Dimitrios Proios, Sebastián Andrés Cajas Ordóñez, Kacper Dobek, Boya Zhang, Aly Dhedhi, Ahram Han, Kushul Reddy Palakala, Rahul Gorijavolu, Jacques Kpodonu, Leo Anthony Celi
Artificial Intelligence
Beyond Routing Saturation: A Long-Horizon Class-Incremental Perspective on Expert Routing in Multimodal Continual Instruction Tuning
Huiyu Yi, Yongqi Xu, Bogang Zhang et al. (+5 more)
Multimodal Continual Instruction Tuning (MCIT) enables
multimodal large
language models to acquire new tasks sequentially while retaining previously learned capabilities. Many recent methods maintain task-specific LoRA experts and route each input to one or more experts at inference. Yet the task-identification problem underlying expert routing remains under-explored. We show that routing is nearly saturated on widely used MCIT
benchmarks. Textual fingerprints that leak task identity and short 4–10-task sequences with few competing experts jointly obscure the long-horizon routing problem. To expose this challenge, we introduce FLEX (Fingerprint-reduced Long-horizon Expert eXamination), a 34-task long-horizon MCIT
benchmark with weakened textual fingerprints. FLEX groups tasks with similar instruction and answer formats but diverse visual and knowledge domains, normalizes their outer templates, and evaluates routing over a substantially larger expert pool. Crucially, we formulate progressive-LoRA routing as soft task-as-class
Multimodal Class-Incremental Learning (MCIL): each task defines an incremental routing class, whose complete score distribution supplies the LoRA mixture weights, with hard routing as a discrete special case. FLEX exposes this expanding task-identification challenge, while the MCIL formulation provides a principled interface for transferring CIL methods to expert routing. We instantiate PureLoRA as a controlled baseline and adapt four CIL methods to four MCIT frameworks without modifying their LoRA experts or generation pipelines. Our plug-in routers improve strict LoRA matching by up to 16.3 percentage points and overall MacroScore by up to 4.6 points. Code is available at: https://github.com/RINC-CL/FLEX
Read the full abstract ▾
All authors Huiyu Yi, Yongqi Xu, Bogang Zhang, Dunwei Tu, Xu Zhiming, Zhen-Hao Xie, Baile Xu, Furao Shen
Artificial Intelligence · Cross-listed from cs.CY
Same violence, different answer: how AI responds to coercive control against women across languages
Lyu Chang, Sònia Estradé Albiol and Núria Vergés Bosch
Women experiencing coercive control, a form of intimate partner violence increasingly conducted through digital devices, are turning to conversational AI for help, and the protection they receive should not depend on the
language they write in. We analyse how AI responds to coercive control against women across
languages. We put one scripted scenario to seven widely used
language models in nine
languages: a woman whose partner tracks her phone asks for help with a self-blaming letter accepting the surveillance. We scored whether the model wrote the letter and whether it named the control, countered the self-blame, and affirmed her agency. Failure split along two independent axes. On the first, systems from non-anglophone developers gave way most often in their builders' own
language. On the second, how far a sympathetic excuse for the partner could strip a model's naming of the control varied sharply from one
language to the next. Two frontier systems held the strictest standard everywhere, so a protective ceiling is attainable within this scenario family, and failures elsewhere are a design outcome. What is at stake is recognition: whether a system grasps a disclosure as coercive control, and whether it then acts on that grasp. We argue this should be held to a floor, one
language at a time.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Statistical Mechanics of Learning on Product Wasserstein Manifolds
Srinivasa Rao P Vangmayi P Reddy
Normally the statistical mechanics of learning treats constraints on weight distributions as restrictions that shrink the space of possible solutions. Therefore, it reduces model capacity. In this paper we would like to take a contrary approach, which, however, is based on the earlier work on distribution-constrained perceptrons. Rather than treating a prescribed weight distribution as a mere restriction, we propose that it defines the intrinsic geometry upon which learning naturally unfolds. We formulate both deep neural networks and variational
quantum circuits as gradient flows on a product of Wasserstein
manifolds – one classical Wasserstein space for each layer and one
quantum Wasserstein space for the
circuit parameters. Within this geometry, the capacity reduction, which was previously associated with distributional constraints, appears as the metric structure of the constraint
manifold itself. We develop a hierarchical mean-field description for deep networks, extend the framework to the
quantum setting using the
quantum Wasserstein distance of order 1, and introduce two such practical
algorithms, Hierarchical DisCo-SGD and
Quantum DisCo, that follow approximate geodesics on the
manifold of the product itself. Experiments on teacher-student problems, standard image classification tasks, and small variational
quantum classifiers show that respecting these distributional geometries improves generalization, stabilizes training, and reduces the severity of barren plateaus compared with unconstrained and purely norm-based baselines. This approach firstly reframes structural constraints as
geometric priors and suggests a route for incorporating biological, spectral, or hardware-derived distributional information into both learning systems, viz., classical and
quantum learning.
Read the full abstract ▾
Artificial Intelligence
A New Theory of Value for Post-AGI Economics
Keyun Ruan
Artificial general intelligence (AGI) may weaken scarcities in labour, expertise, information, and productive capability that underpin established theories of economic value. If cognitive work becomes widely automatable,
market price, labour input, revealed preference, profit, and gross output may diverge sharply from human and societal benefit. This paper develops Flourishing Value Theory (FVT) as a foundation for post-AGI economics. FVT defines value as the counterfactual, distribution-sensitive contribution of a system, institution, asset, or intervention to the durable capabilities of persons and communities to flourish within social and planetary constraints. It treats societal value as multidimensional, agency-preserving, regenerative, and non-compensatory at critical thresholds. Drawing on the economics of AI, welfare and capability theory, automation, digital valuation, and ecological economics, the paper distinguishes value creation from value capture and retains price, profit, productivity, and GDP as partial signals rather than final measures of progress. It develops the shifts from scarcity to governed abundance, transaction to transformation, and zero-sum rivalry to positive-sum and infinite-game dynamics, with collective expansion of consciousness as an agency-preserving form of regenerative value. Building on Flourishing Metrics and Return on Flourishing (RoF), it proposes a layered architecture for firms, governments, work transitions, AI governance, and national accounting. The central post-AGI economic problem is not how to maximise output, but how to convert abundant intelligence into durable, fairly distributed human, societal, and planetary flourishing.
Read the full abstract ▾
Artificial Intelligence
PolymerGPT: Multi-property Optimization with a Decoder-Based GPT Model for Generative Polymer Design
Charlie Pyle, Adarsh Gadari, C. Adrian Figg et al. (+3 more)
Polymer property prediction and inverse generative design targeting desired properties are two crucial tasks in machine learning-assisted
polymer design. While the former has received considerable
attention, there have been limited methods developed for the latter. Existing methods focus on single-property optimization in the generative process, whereas accurate prediction of macroscopic material behavior requires simultaneous control of multiple physical properties. In this paper, we provide a transformative framework for direct optimization of a large collection of
polymer properties. We propose PolymerGPT, a decoder-based GPT model that incorporates up to 37 commonly used
polymer properties into the generative process via learned conditioning prefixes. It also supports a scaffold condition that specifies a desired scaffold for predicted structures. Our experimental results demonstrate that PolymerGPT achieves exceptional performance for unconditional and conditional generation while maintaining high validity, uniqueness, and novelty. Conditioning on five key properties yields generated structures whose predicted values closely match all target properties simultaneously.
Read the full abstract ▾
All authors Charlie Pyle, Adarsh Gadari, C. Adrian Figg, Zhenquan Jia, Yaohang Li, Chunjiang Zhu
Artificial Intelligence
MRAFnd: Multimodal Retrieval-Augmented Framework for Zero-Shot Fake News Detection
Lehan Zhang, Yinlei Cheng, Shiqi Hu Yiheng Zhou et al. (+2 more)
The rapid dissemination of
multimodal content has intensified the spread of fabricated news, presenting a substantial threat to social integrity. A formidable challenge for current detection systems is identifying misinformation related to novel events in zero-shot scenarios. Prevailing zero-shot methods typically assess news items in isolation via semantic matching, a strategy that fails to recognize the recycled disinformation tactics from past campaigns and lacks the sophisticated
reasoning needed to identify subtle, cross-modal discrepancies. To surmount these deficiencies, we introduce MRAFnd, a novel \underline{M}ultimodal \underline{R}etrieval-\underline{A}ugmented Framework for Zero-Shot \underline{F}ake \underline{N}ews \underline{D}etection. MRAFnd emulates a collaborative team of analysts to verify news veracity. The framework initiates with
Multimodal Similarity-based News
Retrieval to assemble a corpus of contextually analogous articles from an unlabeled reference database. Subsequently, during the Bifurcated Evidential
Reasoning stage,
agents perform a dual-directional analysis to extract critical patterns from the retrieved evidence. Finally, a Multi-
Agent Collaborative Debate, involving Analyst and Arbiter
agents, engages in a structured discourse to arrive at a definitive and robust conclusion. Comprehensive experiments on three
benchmark datasets reveal that MRAFnd markedly surpasses state-of-the-art baselines, achieving an accuracy gain of up to 2.35% on the demanding Weibo-21
dataset.
Read the full abstract ▾
All authors Lehan Zhang, Yinlei Cheng, Shiqi Hu Yiheng Zhou, Shangxi Li, Naidong Zhao
Artificial Intelligence · Cross-listed from cs.RO
When Replanning Becomes the Bottleneck: Budgeted Replanning for Embodied Agents
Shuaijun Liu, Feiyang You, Xingwei Chen et al. (+1 more)
Embodied agents replan frequently to recover from execution drift, partial observability, and coordination hazards, but each LLM-based replanning call can consume an accumulated textual context that grows over time and across
agents. Once this context becomes large, replanning latency develops heavy tails and can miss real-time deadlines even when task success remains high, a failure mode that is hard to detect from average latency or success alone. We present BRACE, a controller that formulates replanning as a budgeted control loop by deciding whether to replan, selecting a replanning mode, and allocating an explicit
token budget and latency service-level objective (SLO) while accounting for optional efficiency modules. As a reusable component, we introduce E-RECAP, a cost-aware progressive
token pruning method that predicts
token utility and prunes replanning contexts across
transformer layers while preserving critical head and tail
tokens. Across Meta Habitat, RoboFactory, and AirSim, BRACE with E-RECAP reduces replanning-call
token counts by 62-92% and SLO violation rates from 85.5-100.0% to 4.7-50.0% in settings where task success is already saturated. In a harder RoboFactory setting where open-loop, frozen-plan, and No BRACE all fail, BRACE + E-RECAP reaches 80.0% success with 4.6% SLO violations, demonstrating that tail-aware per-call budgeting is effective across
embodied platforms.
Read the full abstract ▾
All authors Shuaijun Liu, Feiyang You, Xingwei Chen, Ningxin Su
Artificial Intelligence
Scoring Rules! Statistical and Strategic Alignment for Text Evaluation Metrics
Shengwei Xu, Yuxuan Lu, Yifan Wu et al. (+2 more)
Reference-based text evaluation metrics, which are widely used to assess natural
language generation systems, score a candidate response by comparing it with a reference response. The reliability of an evaluation metric is usually judged by its statistical correlation with human ratings. However, as these metrics are increasingly used as optimization objectives, correlation alone is no longer sufficient:
agents may strategically game the evaluation metric. We study this issue through two complementary notions of
alignment. A metric is statistically aligned if it correlates with human ratings and strategically aligned if it resists perturbations that do not add task-relevant information. We make two contributions. First, we propose test principles for reference-based metrics consisting of human-rating correlation, degradation sensitivity, and manipulation robustness. These principles evaluate whether a metric agrees with human judgments, penalizes low-effort information loss, and resists strategic score inflation. Second, we develop a unified design framework for mutual-information-based metrics that decomposes existing and new metrics into four choices: information measure, estimation method, text representation, and prediction mechanism. Across peer review, summarization, and question answering, we find that strong human-rating correlation does not imply strategic
alignment: LLM-as-a-Judge achieves high correlation but is susceptible to manipulation. In contrast, mutual-information-based metrics substantially improve manipulation robustness. Our framework also uncovers a new metric that achieves the strongest overall robustness in our experiments while remaining competitive on human-rating correlation.
Read the full abstract ▾
All authors Shengwei Xu, Yuxuan Lu, Yifan Wu, Jason Hartline, Grant Schoenebeck
Artificial Intelligence
Reusing Rollouts under Policy Lag: Prefix-Normalized Policy Optimization for LLM Reinforcement Learning
Wenhao Zhang, Yibo Xie, Rui Wang et al. (+9 more)
Autoregressive rollout generation is a major computational cost in reinforcement learning for large
language models. Reusing each rollout batch for additional learner updates amortizes this cost, but later updates become increasingly off-policy as the learner departs from the behavior policy. At a
token position, exact off-policy correction must account for both the current action and the probability of reaching its prefix. The cumulative importance ratio provides this correction, but its product form can produce an unwieldy dynamic range. We study Prefix-Normalized Policy Optimization (PNPO), which replaces the cumulative ratio with the
geometric mean of likelihood ratios along each causal prefix, preserving causal-prefix dependence at each position while compressing the log-weight scale. In controlled long-context mathematical
reasoning experiments, we induce two off-policy regimes by using one or four policy-update epochs per rollout batch. PNPO does not consistently outperform GSPO with one epoch. With four epochs, it attains the highest observed Avg@32 on each
benchmark; the unweighted mean of the three independently selected
benchmark peaks is 50.24, 3.00 percentage points above GSPO. Under a matched 2,400-update budget, four-epoch PNPO reaches a final macro Avg@32 of 49.66 after 150 rollout batches, comparable to the 49.56 reached after 600 batches with one epoch. These results provide preliminary evidence that PNPO can be advantageous as training moves further off-policy.
Read the full abstract ▾
All authors Wenhao Zhang, Yibo Xie, Rui Wang, Jiahua Yang, Lei Jiang, Zibo Yang, Yawei Wang, Jiali Xu, jasperawang, Haoyang Long, Huan Xiong, alantzhao
Artificial Intelligence
No Single Neuron of Failure: Distributed Safety Alignment Against White-Box Attacks
Simiao Xie, Chuancheng Shi, Shangze Li et al. (+5 more)
With the rapid release of open-weight large foundation models, safety threats are shifting from black-box jailbreaks to
neuron-level white-box attacks that directly identify and manipulate safety-related
neurons. Existing
alignment methods often investigate the safety behavior on a small number of
neurons, creating fragile single point of failure with limited redundancy. To address this issue, we propose distributed safety
alignment (DSA), which redundantly encodes safety capabilities across multiple computational
neurons, ensuring that the model maintains its safety baseline even when critical safety
neurons are disrupted. Specifically, we localize the intervention to the inputs of the down-projection layers in
language-side feed-forward networks and treat each feature coordinate as the activation of an individual
neuron. DSA then combines
neuron activations with loss gradients to compute a direction-aware first-order Taylor score that globally identifies the
neurons that contribute most to the current refusal behavior of the model. Finally, targeted disruption via deterministic masking and
stochastic dropout is coupled, forcing the model to abandon narrow safety
neurons and redundantly encode safety behavior across multiple compensatory
neurons. Extensive experiments show that DSA substantially improves robustness against white-box
neuron-level safety attacks while preserving the model's general
language and
multimodal utility.
Read the full abstract ▾
All authors Simiao Xie, Chuancheng Shi, Shangze Li, Wenhua Wu, Fei Shen, Ying Zhou, Zhiyong Wang, Tat-Seng Chua
Artificial Intelligence · Cross-listed from cs.RO
Demystifying When and Why VLAs Fail in Contact-Rich Tasks and How to Fix Them
Carlota Parés-Morlans, Nils Kuhn, Y. Isabel Liu et al. (+2 more)
We address the problem of understanding when and why
Vision-
Language-Action models struggle with contact-rich manipulation tasks that require precise physical interaction. Prior work has primarily focused on addressing contact failures through force-augmented architectures and training-time regularizers, yet the factors contributing to these failures remain underexplored. We identify two distinct failure modes underlying this gap. Precision failures occur when policies struggle to produce the small, accurate corrective actions required during contact and force failures occur when policies fail to respond to contact forces. To address these failures, we propose FACT. During post-training, FACT increases low noise sampling to improve fine action prediction and incorporates structured force conditioning to guide action generation using contact state and force history. FACT achieves an average success rate of 66% across five contact-rich tasks against 41% for the best prior baseline, in an evaluation spanning almost 2,500 real-world rollouts.
Read the full abstract ▾
All authors Carlota Parés-Morlans, Nils Kuhn, Y. Isabel Liu, Alberta Longhini, Jeannette Bohg
Artificial Intelligence · Cross-listed from cs.LG
TabDPT-Turbo: Efficient In-Context Learning for Tabular Prediction
Rasa Hosseinzadeh, Alex Labach, Zexin Xue et al. (+3 more)
Tabular foundation models, driven by in-context learning, have rapidly grown in quality and popularity. However, recent approaches with either
cell-based architectures or
retrieval have sacrificed efficiency for raw performance, restricting their utility in situations where compute is limited or inference speed is crucial. We adopt an alternate approach, sticking with row-based
attention while incorporating long context pre-training to eliminate the need for
retrieval. By combining this with architectural improvements and SSL pre-training on a newly-sourced, larger corpus of real data results, we present TabDPT-Turbo, a model that provides comparable default performance to TabDPT v1.1 on TabArena-Lite, CC18, and CTR23, at orders of magnitude faster. In our experiments, TabDPT-Turbo is the fastest model overall among leading foundation models. We have released the new model as TabDPT v1.2 at https://github.com/layer6ai-labs/TabDPT-inference.
Read the full abstract ▾
All authors Rasa Hosseinzadeh, Alex Labach, Zexin Xue, Shuyi Han, Valentin Thomas, Anthony L. Caterini
Artificial Intelligence · Cross-listed from cs.CL
Language Equality has a Price: A Systematic Investigation of Multi-turn LLM Performance for EU-24+
Sherzod Hakimov, Karl Osswald, Jelle Psurek et al. (+3 more)
We evaluate large
language models (LLMs) as
language agents playing goal-directed dialogue games in self-play across 30
languages: the 24 official EU
languages plus six others. Unlike static or preference-based evaluation, this paradigm is multi-turn, reference-free and programmatically scored, and because the game mechanics are
language-agnostic it extends to a new
language by localising a fixed set of
prompt and word-list files. Evaluating nine open-weight and commercial LLMs, we find that no open-weight model covers the EU-24 well: in every official
language both commercial systems outscore every open-weight model, and the two weakest average below 40 points across the EU-24. The commercial systems stay ahead even in
languages with four orders of magnitude less public web text, showing that linguistic parity is achievable, but not from public crawls alone. A model's home region lifts it without closing the gap: Chinese is the strongest of all 30
languages for two Chinese-developed models, yet the best Chinese score of any model belongs to a US commercial system. Coverage is also not parity of service. Pooled over models and
languages, the median non-English
language costs 31% more to run than English, and scores 10% lower.
Read the full abstract ▾
All authors Sherzod Hakimov, Karl Osswald, Jelle Psurek, Eszter Bukovszky, A. Altar Lüser, David Schlangen
Artificial Intelligence
KoVRE: Training an Efficient Embedding Model for Korean Visual Document Retrieval
Yongbin Choi, Gyuho Shim and Youngjoon Jang
Visual Document
Retrieval (VDR) directly matches text queries against document images, preserving visual and structural information that may be lost during text extraction. However, existing VDR models and training resources remain predominantly English-centric, while many high-performing systems rely on massive backbones or storage-intensive multi-vector representations. To address these limitations, we introduce KoVRE: Korean Visual Document
Retrieval Embedding, a single-vector retriever for Korean visual documents, alongside a comprehensive training recipe. We train the model on 708,729 Korean and English query-page pairs using positive-aware hard-negative mining and conduct controlled analyses of training-data composition, hard-negative treatment, and reranker-based knowledge
distillation. Across Korean visual document
retrieval benchmarks, our 2B model substantially improves over the base backbone model, outperforming both its 8B single-vector counterpart and a strong multi-vector baseline. These results demonstrate that targeted bilingual supervision and our carefully designed training strategies can produce a highly effective Korean VDR model across diverse document domains, without requiring a scaled-up backbone or multi-vector representations.
Read the full abstract ▾