Artificial Intelligence · Cross-listed from cs.LG
Linear Attention Architectures: Mechanisms, Trade-offs, and Cross-Layer Routing
Tommaso Cerruti, Tim Rieder, George Rowlands et al. (+2 more)
Self-
attention lets each
token retrieve information from the full context, but its quadratic cost in sequence length limits training and inference at long context. This paper presents a comparative study of softmax
attention and four recent recurrent linear-
attention architectures: DeltaNet, Gated DeltaNet, Kimi Delta
Attention, and Gated DeltaNet-2. We express these mechanisms in a common recurrent-
memory notation, making explicit how they differ in expressivity,
memory decay, erase and write control, training throughput, and implementation complexity. Our experiments center on 350M-parameter models trained for 15B
tokens, and include optimizer and learning-rate comparisons, hybrid-versus-pure stack comparisons, sequence-length runtime measurements, larger DeltaNet runs at 1.3B and 3B parameters, and a small set of downstream evaluations. The reported speed results measure training throughput and iteration time; we do not provide an empirical inference-speed
benchmark. Within the reported 350M-parameter, 15B-
token sweep, Kimi Delta
Attention with
Muon reaches the lowest final validation loss, a pure Gated DeltaNet stack trained with AdamW has the highest normalized training throughput, hybrid stacks generally improve loss at a throughput cost, and
Muon consistently lowers final validation loss relative to AdamW in the matched architecture settings we evaluate. We introduce and evaluate lightweight cross-layer routing mechanisms for DeltaNet-style
memories. The most natural DeltaNet-inspired formulation, forwarding a lower layer's delta-rule write error into the next layer's value target, does not improve over matched baselines. Routing into the aligned hidden stream and forwarding the write value instead yields a modest improvement in the matched runs we report: Cross-Layer Value Routing (CLVR) lowers final validation loss for both DeltaNet and Gated DeltaNet.
Read the full abstract ▾
All authors Tommaso Cerruti, Tim Rieder, George Rowlands, Lingfeng Jin, Imanol Schlag
Artificial Intelligence · Cross-listed from cs.LG
path_boost: A Python Package for Interpretable Graph-Level Prediction using Path-Based Gradient Boosting
Claudio Meggio, Johan Pensar and Riccardo De Bin
We present path_boost, a Python package for interpretable supervised learning on graph-structured input data. The package implements PathBoost, a gradient boosting
algorithm that automatically discovers predictive labeled paths within graphs during the learning process. Unlike graph neural networks, which are generally difficult to interpret, PathBoost produces an additive prediction model over path-based features that explicitly reveals which substructures drive predictions. To avoid an exhaustive enumeration of all possible paths, the
algorithm iteratively selects and extends paths during learning based on their predictive power, using boosting to combine weak learners into a strong ensemble. The package supports both regression and binary classification. Key features include compatibility with scikit-learn workflows, support for custom base learners and selectors, automatic starting node selection, parallel training across anchor nodes, and built-in variable importance computation. We demonstrate PathBoost on molecular property prediction of transition metal compounds, where atoms serve as nodes and bonds as edges, and further
benchmark PathBoost against an established graph neural network and a graph kernel method across six molecular
datasets. The package is available on PyPI and GitHub under an open-source license.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Adversarial Decoys: Misdirecting Attention-Based Defenses in ViT
Giulia Marchiori Pietrosanti, Giulio Rossolini and Giorgio Buttazzo
Vision Transformers (ViTs) remain vulnerable to localized
adversarial attacks, e.g.,
adversarial patches, while recent test-time defenses mitigate them by suppressing image
tokens with abnormally high
attention scores. These defenses exploit a strong coupling between
attention and
adversarial effectiveness:
adversarial tokens often need to attract substantial
attention to influence the prediction. We introduce
adversarial decoys, independently optimized image patches that redirect the
attention, and therefore related defenses, toward selected target
tokens. Rather than jointly optimizing misclassifications and defense evasion, our approach decouples the two objectives: the original
adversarial region induces the incorrect prediction, while a separate decoy manipulates the
attention ranking used by the defense. A layer-wise objective increases target-
token attention and promotes these
tokens above competing non-target ones. Since the decoy is optimized independently of the underlying attack, the method is attack-agnostic and can be easily integrated with any existing
adversarial patch attack. Experiments on ImageNet across multiple ViT architectures and attacks show that decoys can redirect high
attention scores away from the true
adversarial region while preserving much of the attack effectiveness. These results reveal a fundamental limitation of using
attention magnitude as an indicator of
adversarial relevance.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Efficient Safety Alignment of Language Models via Latent Personality Traits
Mohamed Amine Merzouk, Nolan Smyth, Damiano Fornasiere et al. (+3 more)
Current safety methods for large
language models are known to be vulnerable to
adversarial attacks, motivating research into robust alternatives. Latent
Adversarial Training (LAT) is among the most effective defenses, but can degrade utility and requires training on large
datasets of harmful
prompts. We introduce Latent Personality
Alignment (LPA), which replaces explicit harm refusal with
adversarial training on just 66 harm-agnostic statements drawn from psychometric personality literature. We hypothesize that personality-anchored representations share latent structure with harm avoidance, so adversarially stabilizing them implicitly constrains the subspace exploited by jailbreak attacks. LPA achieves near-zero attack success rates on HarmBench across direct requests and five jailbreak methods, despite never seeing harmful content during training and no loss of performance on standard
benchmarks. Moreover, the training process is lightweight; the entire procedure completes in minutes on a single GPU and uses 75x fewer examples than standard LAT. Extensive ablations demonstrate the robustness, efficiency, and generalization of our method.
Read the full abstract ▾
All authors Mohamed Amine Merzouk, Nolan Smyth, Damiano Fornasiere, Linh Le, David Williams-King, Adam Oberman
Artificial Intelligence
Persona Cartography: Charting Language Model Personality Traits in Weight Space
Luke Baines, Anton Gonzalvez Hawthorne, Mariia Koroliuk et al. (+4 more)
Large
language models exhibit recurring behavioural patterns – personas – that shape generalisation and safety, but we lack reliable tools for decomposing, measuring, and controlling them. Our central insight is to treat personas as positions in a space of behavioural traits, using the OCEAN framework to describe model personas in terms of Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism. We train low-rank adapters to amplify or suppress individual traits, and evaluate their effects using an LLM-judge calibrated against a human-validated panel, trait-specific multiple-choice
benchmarks, and standard capability evaluations. Across six models from three families (4B-32B), we find that each adapter moves its target trait largely monotonically with scale, combines approximately additively with other adapters to construct mixed personas, and preserves performance on capability
benchmarks at moderate scales. We further show that the induced trait axes affect safety-relevant behaviour in downstream evaluations: for example, moving along neuroticism and agreeableness axes affects frustration and sycophancy respectively. We also introduce an unsupervised psychometric pipeline that recovers four interpretable behavioural factors (tone, initiative, didacticism, epistemic caution) from model rollouts. Persona control can then be considered in terms of learning, scaling, and composing traits in weight space, providing a bridge between personality measurement, model editing, and safety.
Read the full abstract ▾
All authors Luke Baines, Anton Gonzalvez Hawthorne, Mariia Koroliuk, Irakli Shalibashvili, Clément Dumas, Konstantinos Voudouris, David Demitri Africa
Artificial Intelligence · Cross-listed from cs.LG
Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu et al. (+1 more)
With the growing adoption of VLMs, DMs, LLMs, and AFMs, these
multimodal foundation models can inadvertently encode sensitive, copyrighted, biased, or unsafe cross-modal associations that originate from their training data. Retraining after deletion requests or policy updates is often impractical, and targeted forgetting remains difficult because knowledge is distributed across shared representations.
Multimodal unlearning addresses this challenge by enabling selective removal across modalities while retaining overall utility. This survey offers a unified, system-oriented view of
multimodal unlearning across
vision,
language, audio, and
video, grounded in recent advances, emerging applications, and open problems. Our taxonomy enables systematic comparison across model architectures and modalities, clarifying trade-offs among deletion strength, retention, efficiency, reversibility, and robustness. This survey highlights open problems and practical considerations to support future research and deployment of
multimodal unlearning. We release a curated repository: https://smsnobin77.github.io/Awesome-
Multimodal-Unlearning/
Read the full abstract ▾
All authors Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu, Vaidehi Patil
Artificial Intelligence · Cross-listed from cs.CR
Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs
Anupam Wagle, Ifrat Ikhtear Uddin, Chaowei Zhang et al. (+1 more)
Large
language models (LLMs) exhibit remarkable capabilities but remain highly vulnerable to
adversarial prompts and jailbreak attacks. Existing approaches primarily analyze these failures through input-output behaviors or attribution methods, offering limited insight into how
adversarial perturbations alter the model's internal
reasoning. Consequently, the mechanisms underlying unsafe or incorrect behaviors remain poorly understood. We introduce a mechanistic framework for diagnosing LLM vulnerabilities using paired internal computation graphs, which represent
prompt-specific inference as structured causal interactions among latent features. By constructing and aligning computation graphs for clean and attacked
prompts, we reveal that
adversarial attacks induce systematic transformations of internal
reasoning, including suppression of safety-relevant components, emergence of attack-specific features, and rerouting of computation paths. Building on this representation, we propose a unified framework that (i) decomposes computation into invariant, suppressed, and emergent structures, (ii) identifies recurring vulnerability motifs associated with failure modes, and (iii) performs causal interventions on nodes, paths, and subgraphs to directly evaluate their contributions to attack success. This enables a transition from descriptive attribution to causal diagnosis of model failures. Experiments across multiple open-source LLMs and diverse
adversarial and jailbreak
benchmarks demonstrate that structural deviations in internal computation graphs strongly correlate with unsafe behaviors. Furthermore, targeted interventions on identified vulnerability motifs improve model robustness, establishing internal computation graphs as a principled foundation for understanding, diagnosing, and mitigating LLM vulnerabilities.
Read the full abstract ▾
All authors Anupam Wagle, Ifrat Ikhtear Uddin, Chaowei Zhang, Longwei Wang
Artificial Intelligence · Cross-listed from cs.CR
Closed-Loop Dynamic Validator Node Scaling in Private Substrate Blockchains Using Takagi-Sugeno Fuzzy Inference
Thandile Nododile, Ayinde M. Usman and Clement N. Nyirenda
Private blockchain networks run with fixed node configurations that cannot adapt to changing workload conditions. Too many nodes serving a light workload waste resources; too few nodes facing heavy demand slow block production and degrade finalisation. The right validator count is hard to determine, as it depends on overlapping factors that shift over time. This paper presents a Takagi-Sugeno (TS) fuzzy inference system that reads live blockchain parameters (block production time, block size, and active node count) and outputs a continuous efficiency score alongside a scaling recommendation: Scale Up, Maintain, or Scale Down. The controller uses triangular membership functions across three linguistic variables, evaluated through a complete 27-rule base with product t-norm aggregation. A key contribution is an empirical recalibration of the membership functions, anchoring linguistic terms to the observed operating range of the testbed rather than to theoretical extremes. The system is evaluated on a 10-node Substrate blockchain network storing real smart water meter data hashes from the Queensland Government open data portal. Statistical analysis across configurations of 4, 7, and 10 active nodes confirms that the controller produces distinct operational profiles reflecting each configuration's provisioning state. In closed-loop experiments, the controller autonomously adjusts validator participation in both directions, activating validators under rising load and removing them under over-provisioning, converging to the same stable
equilibrium from both directions. Compared against three threshold-based baselines, it shows fewer scaling oscillations while maintaining comparable block production times. Results show that TS fuzzy inference can support autonomous validator management in private blockchain deployments, with stable scaling behaviour threshold approaches cannot match.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
How Do I Know What to Say Next? Barenholtz's Autogenerative Theory as an Enrichment of Harrisean Integrationism
J. Mark Bishop and Stephen J. Cowley
Roy Harris's Integrationist linguistics offers a compelling critique of the referentialist tradition embedded deep at the heart of computational approaches to
language, arguing that
language is not a code that maps onto a pre-given world but a situated, bipartite activity oriented toward prospective joint action. Yet Integrationism leaves certain explanatory gaps: it does not fully account for the structural mechanism by which signs sustain prospective openness, it undertheorises the continuity between linguistic and non-linguistic semiotic activity, and it offers no detailed account of the structural properties of the accumulated archive of past integrations. This paper argues that Elan Barenholtz's autogenerative theory of
language, developed in response to the behaviour of Large
Language Models (LLMs), can fill precisely these gaps, enriching Integrationism without undermining any of its core commitments. Specifically, the autogenerative account provides: a structural mechanism for the prospective openness that Harris identifies as central to bipartite communication; a computational correlate for Harris's thesis of semiotic continuity between
language and other sign-making activity; and a theory of the archive: what the accumulated residue of past integrations looks like and how new participants draw upon it. The synthesis preserves Harris's ontological primacy of the situated integrative act while adding explanatory content that Integrationism itself does not supply. For practitioners and researchers in natural
language processing and large
language model design, the argument offers a principled account of what the statistical structure that LLMs so effectively exploit actually is, and of what it cannot, by its nature, provide.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
Time-to-Collision Based Dynamic Obstacle Avoidance Using Pretrained Vision Models for Robots in Unstructured Environments
Erik Jagnandan, Mulugeta Haile, Gregory Barber et al. (+1 more)
Dynamic obstacle avoidance in unstructured outdoor environments remains a critical challenge for autonomous mobile
robots, particularly when large-scale
robot-specific training data and simulation-based policies are impractical. We present a data-efficient, interpretable method for
vision-based dynamic obstacle avoidance that operates entirely on real-world data, avoiding the sim-to-real transfer problem inherent in simulation-trained policies. Our approach leverages UniDepth, a large pretrained
monocular depth estimation model, to produce dense depth maps from RGB
video without requiring stereo cameras or
LiDAR at inference time. Dynamic obstacle avoidance is achieved by extending the SuperPoint and SuperGlue feature correspondence pipeline to track keypoints across long frame sequences, projecting their 2D pixel-space positions into 3D using camera intrinsics and predicted depth, running bundle adjustment initialized from these 3D keypoints, and computing per-keypoint time-to-collision (TTC). A 2D motion primitive in the ground plane is then selected to move the
robot away from the closest point of approach of the minimum-TTC keypoint. Evaluated on real-world data from the M3ED
dataset, our pipeline achieves a precision of 0.49 and a recall of 0.38 in identifying frames with a ground truth TTC below 1 second, and correctly generates the evasive motion direction in 84% of true positive detections. Crucially, it detects at least one frame with TTC less than 1 second for 20 out of 22 unique physical obstacles present in our test sequences. Unlike end-to-end learned methods that demand thousands of hours of
robot-specific training data, our approach eliminates model training entirely, requiring only 74 seconds of data for hyperparameter tuning. This demonstrates exceptional data efficiency while preserving interpretable and generalizable behavior across diverse obstacle types.
Read the full abstract ▾
All authors Erik Jagnandan, Mulugeta Haile, Gregory Barber, Pratik Chaudhari
Artificial Intelligence
Nigeria Machinery: A Low-Resource Industrial Dataset with a Domain-Grounded Reasoning Layer
Gospel Bassey and Vincent Fakiyesi
There is relatively little, public, and model-ready data on industrial machinery for African economies. This makes it hard to do quantitative analysis or to train
language models on numeric tasks grounded in that setting. We release two things to help with part of this problem. The first is the Nigeria Machinery Usage and Failures
Dataset: 89 machine-level records across 28 indicators, covering Nigeria's manufacturing and oil and gas sectors from 2006 to 2025. Every record names a public source and is decoded by a codebook. The second is a method for building chain-of-thought (CoT)
reasoning examples from these sparse numeric values. The result is 94
prompt, completion, and
reasoning-trace rows. In every row, the
prompt names the real indicator, subsector, year, and source of the record it comes from. The data adaptation work was carried out by Adaption Labs. Along the way we describe a problem that is common when
language models are used to build
datasets. The
prompts can match the real numbers while saying nothing about the real domain. We show that fixing this raises the share of domain-grounded
prompts from 1 out of 78 in an earlier release to 94 out of 94, and that every
retrieval answer now matches its source value (84 out of 84). We release the data, the
reasoning layer, and a per-row provenance file under CC-BY-4.0. We are clear about the limits. With 89 records and 17 indicators that have only one observation, this is a reference and seed
dataset, not a large training set. Most
reasoning rows are
retrieval rather than multi-step computation.
Read the full abstract ▾
Artificial Intelligence
Feedback Manipulation Regularization: Enabling Offline Agent Alignment for Imitation Learning
Benjamin Poole and Minwoo Lee
Reinforcement learning (RL) research has increasingly shifted focus towards
alignment, ensuring
agents learn behaviors adhering to human values. While human demonstrations and feedback have proven crucial for
alignment, existing approaches predominantly combine these signals using multi-stage pipelines designed for the contextual bandit framing of
language generation. Yet little work explores how these complementary inputs can serve as a richer, interconnected signal for single-stage offline training in fully sequential decision-making environments. We propose Feedback Manipulation Regularization (FMR), an
algorithm-agnostic method that harnesses evaluative feedback as a corrective signal to improve the
alignment of imitation learning policies. We adapt Safety Gymnasium environments to be a principled testbed for
alignment evaluation, demonstrating improved aptitude and up to a 98% reduction in misalignment across a range of imitation learning
algorithms. FMR remains robust in limited data regimes, even when learning from scarce aligned and uninformative noisy demonstrations.
Read the full abstract ▾
Artificial Intelligence
Agentic AI and Retrieval-Augmented Models in Straight-Through Underwriting
Robert Richardson, Josh Meyers, Brian Hartman et al. (+1 more)
Artificial intelligence (AI) is beginning to reshape actuarial practice, particularly in domains that require
reasoning over unstructured documents, heterogeneous data sources, and regulated decision workflows. Actuaries now face a design space that ranges from traditional rule-based automation to large
language models (LLMs),
retrieval-augmented generation (RAG), and multi-
agent “agentic” systems that plan, retrieve, call tools, and reflect. This paper examines how these emerging architectures can support actuarial priorities such as transparency, auditability, and human-in-the-loop governance, with a focus on straight-through decision processes. To make these ideas concrete, we develop and analyze an agentic AI framework for straight-through underwriting of small commercial Business Owner Policies (BOPs). We construct a synthetic but realistic experimental environment and compare three underwriting pipelines: (i) a single-LLM baseline, (ii) a naive RAG system, and (iii) a multi-
agent “Agentic RAG” pipeline that combines targeted
retrieval, third-party data checks, and explicit multi-step rule evaluation. The agentic system performs best overall, with the largest gains in multi-step and missing-information scenarios, where structured
retrieval and reflection help the model avoid unsupported straight-through decisions.
Read the full abstract ▾
All authors Robert Richardson, Josh Meyers, Brian Hartman, David Sandberg
Artificial Intelligence · Cross-listed from quant-ph
Multi-agent Autoformalization of Tensor Network Theory
Sirui Lu, Erickson Tjoa and J. Ignacio Cirac
We build a team of specialized large
language-model
agents and present an
agent-driven workflow for research-level formalization in theoretical physics, with the autoformalization of the fundamental
theorem of
matrix-product states as a demonstration. The
agents, coordinated through a structured mathematical blueprint and periodic human review, orchestrated and executed the full formalization autonomously. For some statements, the
agents were able to explore new proof routes that are not part of the standard literature. Along the way the
agents produced extensive tensor-network and
quantum-information libraries not previously available in Mathlib, Lean's mathematical library. As a physical application, the formalization also extends towards
symmetry-protected topological phases in one dimension. We find that the main bottleneck in large-scale autoformalization is enforcing mathematical intent and we provide a detailed study of the full process and various subtleties involved. We release the codebase as the library \href{https://github.com/LionSR/TNLean}{TNLean}, together with a \nChapters{}-chapter \href{https://lionsr.github.io/TNLean/blueprint/}{blueprint} of the formalization effort.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from math-ph
Kime-Representation Formulations of Three Open Problems in the Foundations of Classical Mechanics: Uncertainty, Invariant Entropy, and Directional Degrees of Freedom
Ivo D. Dinov
We give mathematically self-contained formulations, in the complex-time (kime) representation, of three open problems from the foundations of classical mechanics: (I) the extension of the classical entropic uncertainty principle to non-canonical variables and to multiple degrees of freedom; (II) the characterization of coordinate-invariant measures and
entropies, i.e., the question of why continuous physical quantities must be paired for an invariant
entropy to exist; and (III) the construction of a classical relativistic directional degree of freedom (a classical analogue of a
spin-1/2 system). Throughout, the kime phase is interpreted {statistically as a latent circular random variable whose law \Phi models the intrinsic trial-to-trial variability of repeated, identically controlled experiments indexed by the kime magnitude. The mathematical bridge is an exact
symplectic identification of the kime cone with the action-angle chart of a one-degree-of-freedom phase space, under which the kime measure is the Liouville measure and the phase law becomes the angular conditional of a Liouville density. Specifically, we (i) prove a sharp entropic uncertainty relation on the kime cylinder whose extremal family is von Mises x Gaussian, together with a sharp circular Fisher-information inequality saturated exactly by von Mises laws; (ii) prove an exact non-canonical uncertainty relation in which the correction term is the
geometric mean of the Poisson bracket, clarifying the conjectured role of the expected bracket; (iii) prove aggregate multi-degree-of-freedom bounds via the Williamson normal form and Fischer's inequality, and isolate the per-degree-of-freedom refinement as a precise open problem of
symplectic Schur-Horn type; (iv) prove that
diffusion of the kime phase produces monotone
entropy growth with the equipartitioned (Haar-uniform) phase law.
Read the full abstract ▾
Artificial Intelligence
A Graph Neural Network Model for Real-Time Gesture Recognition Based on sEMG Signals
Pragatheeswaran Vipulanandan, Kamal Premaratne and Manohar Murthi
For seemless control of advanced hand prostheses and augmented reality, accurate and immediate hand gestures recognition is essential. Surface electromyography (sEMG) signals obtained from the forearm are commonly employed for this purpose. In this paper, we present a novel approach for sEMG representation that utilizes graph networks which contain information about muscle activation patterns in the forearm. Based on these graph networks, we have developed a machine learning
algorithm capable of real-time hand gesture recognition using a graph neural network. The
algorithm's performance was evaluated using sEMG signals acquired from myoband, which has 8 electrodes placed around the forearm, involving 8 healthy subjects. The proposed method demonstrated an average classification accuracy of 99%, surpassing the performance of state-of-the-art techniques. The average time for both graph construction and prediction stood at 48ms utilizing a M1 pro CPU, rendering the approach well-suited for real-time applications.
Read the full abstract ▾
Artificial Intelligence
VectorizationLLM: Smart Vectorization Based AI Assistant
Ryan Duke
VectorizationLLM is a specialized Large
Language Model based on Google open-weight LLMs. The model is designed to assist students to learn smart vectorization, time/wave vector analysis, piecewise functions,
Fourier analysis, and differential equations in MATLAB. The course application is CTEC 247: Applied Computational Analysis II by the Department of Electrical & Computer Engineering Technology at New York Institute of Technology Old Westbury. The LLM model is designed to be an instructive assistant, providing detailed explanations of concepts with examples from in-class notes without providing direct answers to questions. The model is designed with a RAG (
Retrieval Augmented Generation) knowledge base and system
prompt architecture. Examples in both code, text, and images are provided in the LLM responses.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
Shift & Drift: A Zero-Shot Benchmark for Generalizable and Robust Autonomous Driving Motion Planning
Alessandro Canevaro, Hang Yu, Julian Schmidt et al. (+5 more)
While closed-loop motion planners trained on large-scale, object-level
datasets, e.g., nuPlan, demonstrate strong in-distribution (ID) performance, their generalization to novel urban
topologies and recovery mechanisms following execution perturbations remain under-explored. To address this, we present Shift & Drift, a novel dual-track
benchmark designed to rigorously stress-test motion planners across two critical axes of distribution shift: (1) The Semantic Shift Track leverages a novel conversion pipeline that transforms the aerial, DeepScenario Open 3D
dataset into the nuPlan simulation framework. This enables zero-shot evaluation of planners trained on North American and Singaporean data against 1,182 scenarios spanning four German cities and the US city of San Francisco featuring dense pedestrian-cyclist interactions. (2) The State-Distribution Drift Track injects
stochastic perturbations into the ego vehicle's dynamics to quantify robustness against compounding execution errors. Based on this, we systematically evaluate the failure modes of diverse planning paradigms under semantic and state-distribution shifts. While imitation learning methods achieve high scores in ID
benchmarks, they exhibit significant failures under semantic shift, particularly in pedestrian-dense environments, and suffer from persistent drift when subjected to temporally correlated actuation noise. In contrast, the evaluated reinforcement-learning-based planner demonstrates more graceful degradation, maintaining higher safety and progress metrics across both tracks. Our findings reveal an empirical trade-off between imitation fidelity and closed-loop resilience, providing the community with a rigorous
benchmark to evaluate progress toward reliable deployment.
Read the full abstract ▾
All authors Alessandro Canevaro, Hang Yu, Julian Schmidt, Peizheng Li, Silvan Lindner, Wilhelm Stork, Georg Martius, Julian Jordan
Artificial Intelligence
Infinity-Parser2 Technical Report
Zuming Huang, Jun Huang, Kexuan Ren et al. (+12 more)
We present Infinity-Parser2, a large
multimodal model that couples a controllable data-synthesis pipeline with multi-task reinforcement learning for end-to-end document parsing, addressing the persistent scarcity of faithfully annotated parsing corpora. Our contributions are threefold. First, we build a scalable synthesis engine, pairing a controllable rendering framework with an iterative refinement loop, and use it to construct and open-source Infinity-Doc2-5M: a 5-million-sample bilingual (Chinese/English) corpus spanning diverse document types, annotated with element bounding boxes, canonical content forms (Markdown, HTML, LaTeX, SMILES, structured charts), and full-page reading order. Second, we introduce a verifiable, multi-task reward system that enables Joint Reinforcement Learning across eight co-trained objectives (document parsing, layout analysis, table parsing, math formula parsing, chart parsing, chemical formula parsing, document VQA, and general
multimodal understanding), unifying perception, structure, and
reasoning in a single optimization signal. Third, we release two variants under a shared architecture: Infinity-Parser2-Flash, optimized for low-latency inference with a 3.68x throughput gain over Infinity-Parser-7B, and Infinity-Parser2-Pro, engineered for precision-critical settings. Infinity-Parser2-Pro reaches state-of-the-art 87.6% on olmOCR-Bench and 74.3% on ParseBench, surpassing DeepSeek-OCR-2, PaddleOCR-VL-1.5, and MinerU2.5, with strong generalization to charts, chemical formulas, and document VQA.
Read the full abstract ▾
All authors Zuming Huang, Jun Huang, Kexuan Ren, Baode Wang, Weizhen Li, Jianming Feng, Yu Wang, Yichen Yao, Shijun Lin, Yige Tang, Cheng Peng, Weidi Xu, Wei Chu, Yinghui Xu, Yuan Qi
Artificial Intelligence · Cross-listed from cs.MA
From Triggers to Emotions: A CPM-Grounded Appraisal Multi-Agent for Dynamic Emotional Evolution in Persona-Based Dialogue
Jingyao Cai, Shuaijun Liu, Abdul Rehman et al. (+6 more)
Large
Language Models (LLMs) have substantially advanced persona-based dialogue
agents for
emotion-sensitive role simulation in healthcare, education, counseling, customer service, and interactive storytelling. However, two related lines of work leave a key gap. Persona-based dialogue systems often encode
emotions as static traits or surface-level stylistic cues, and affective dialogue research has largely focused on empathetic response generation toward users rather than modeling the
agent persona's own evolving emotional state. As a result, trigger-driven emotional
evolution within a character remains underexplored. To address this limitation, we draw inspiration from the Component Process Model (CPM), a psychological theory that views
emotion as a dynamic process shaped by the appraisal of external events. We propose CPM-MultiAgent, a CPM-grounded
emotion evolution multi-
agent framework for supporting emotional changes in persona-based dialogue. Instead of treating a character's
emotion as a fixed attribute, CPM-MultiAgent represents it as a latent state that is continuously reshaped by dialogue triggers. Through affective trigger extraction, CPM-based collaborative appraisal, and
emotion state updating, the framework enables more emotionally consistent role simulation in multi-turn interactions.Experiments with baseline comparisons, ablation studies, human evaluation, and case analyses demonstrate that CPM-MultiAgent effectively models dynamic emotional
evolution in emotionally sensitive role-simulation settings.
Read the full abstract ▾
All authors Jingyao Cai, Shuaijun Liu, Abdul Rehman, Yutong Guo, Qin Tian, Thomas Dolby, Sue Green, Chantel Cox, Xiaosong Yang
Artificial Intelligence · Cross-listed from cs.CV
DreamCharacter-1: From 3D Generative Foundation Models to Product-Ready Character Generation
Weizhe Liu, Yunjie Wu, Xiangqian Shu et al. (+5 more)
We present DreamCharacter-1, a lightweight post-adaptation framework that calibrates pretrained 3D foundation models toward high-fidelity, production-ready 3D character generation. Building upon a 3D foundation backbone, our pipeline incorporates three task-oriented components: (1) geometry post-training, which enhances fine-grained surface details through
geometric preference optimization; (2) texture post-training, which synthesizes high-resolution textures and refines the appearance of occluded regions; and (3) inference acceleration, which enables scalable deployment. Extensive quantitative and qualitative experiments demonstrate that DreamCharacter-1 produces visually compelling and structurally robust 3D character assets, consistently surpassing state-of-the-art character generation methods.
Read the full abstract ▾
All authors Weizhe Liu, Yunjie Wu, Xiangqian Shu, Guangwei Wang, Xiangyu Xu, Peng Li, Yujie Li, Hengkai Guo
Artificial Intelligence · Cross-listed from cs.CL
From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier
Eric Jiang, Xiao Liang, Junyi Zhang et al. (+38 more)
Large
language models have made rapid progress in generating machine-checked proofs for well-defined mathematical problems. Extending this progress to research mathematics requires more than solving isolated
theorems. Research involves choosing questions, developing definitions and
conjectures, connecting results, and combining formal proofs with expert judgment. This survey examines how LLM-driven systems can support these broader activities. We review formal-mathematics tasks,
datasets, and autoformalization, and organize proof-generation methods into three overlapping areas: training strategies, inference-time search and adaptation, and agentic workflows. We then examine
benchmark results, selected research projects, and platforms for collaborative mathematical work. A central distinction runs throughout the survey: checking a formal proof does not by itself establish that it captures the intended problem or makes a new mathematical contribution. We therefore distinguish
theorem benchmarks, repository tasks, formalization projects, and research claims, and discuss the evidence needed to assess each. Finally, we identify five priorities for progress: better data and evaluation, representations of mathematical relationships,
conjecture and concept generation, reliable tool integration, and human–AI collaboration. Together, these perspectives connect advances in proof generation to the practical demands of mathematical research.
Read the full abstract ▾
All authors Eric Jiang, Xiao Liang, Junyi Zhang, Justin Baker, Zhi Zhang, Yingjia Wan, Yubei Li, Jinxi Yu, Mengting Li, Haikang Deng, Alexander Taylor, Rushil Raghavan, Michael Simon, Hyunsik Chae, Jia-Chen Gu, Xinjie He, Kyle Hess, Ethan Ji, Yiwen Kou, Tzu-Han Lin, Jiachen Lu, Jack Mauro, Vigyan Sahai, Zheng Tan, Hengli Li, Yikai Zhang, Kyle Zheng, Lunji Zhu, Dong Liu, Jasdeep Sidhu, Isaac Hair, Eniuce Jun, Ying Nian Wu, Andrea L. Bertozzi, Kai-Wei Chang, Raghu Meka, Matthew Sottile, Nanyun Peng, Amit Sahai, Terence Tao, Wei Wang
Artificial Intelligence
Idiobionics: The Unification of Privacy and Intelligent Robotic Prostheses
Kwesi Afari Darfoor, Patrick M. Pilarski and Bailey Kacsmar
The human body is at the center of a growing family of technologies designed to tightly and persistently couple biological and digital systems. Robotic prostheses are a representative example of this tight coupling. Also referred to as bionic limbs, robotic prostheses are devices that support people who have lost limbs in pursuing daily life activities such as walking and grasping objects. Bionic limbs are now perceptive and responsive owing to their integration with advanced sensors and artificial intelligence-based control approaches. Consequently, such robotic prostheses can now be viewed as semiautonomous wearable robotic systems that can co-adapt with their users. However, the same sensing and control advancements that increase the capability of robotic prostheses also introduce threat vectors that could be exploited by malicious entities to violate the
privacy of users. To fully realize the benefits of next-generation bionic limbs, we maintain it is important to directly understand and address these
privacy risks and the barriers they might present to user adoption. This paper therefore introduces a new line of inquiry we term idiobionics to holistically investigate issues at the intersection of
privacy and intelligent bionic limbs. As the main contribution of this paper, we define idiobionics, ground it in related literature, and provide preliminary evidence showing and discussing potential
adversarial attacks that could exploit intelligent bionic limb designs. We then contribute a curated list of open research questions within idiobionics that are relevant to researchers in wearable robotics and other human-facing autonomous systems. We expect that idiobionics research will help unlock the full potential of robotic prostheses and related bionic devices.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Graph-Regularized Deep Learning for EEG-Based Emotion Recognition with Psychologically-Grounded Label Structure
Dongyang Kuang, Zizheng Ma, Yushan Zhang et al. (+1 more)
EEG-based
emotion recognition is critical for mental health monitoring and affective
brain-computer interfaces, yet existing deep learning approaches often treat
emotion classes as isolated labels, ignoring their psychological interdependencies. We propose a graph-regularized learning framework that conceptualizes
emotions as nodes in a graph where edges encode proximity based on dimensional
emotion theories. We adapt three complementary regularization strategies–Graph Label Smoothing (intuitive soft labeling), Commuting distance on graph via Graph
Laplacian (spectral graph theory), and Sliced Wasserstein Distance (optimal transport on graph)–ordered by increasing computational complexity. These strategies penalize model predictions that deviate from the established
emotion topology. Our framework is evaluated across three representative backbone architectures: AudioTransformer (pure
transformer), Conformer (CNN-
transformer hybrid), and DCGNN (causal graph neural network), demonstrating architecture-agnostic benefits. Experiments on SEED-IV (4 classes) and SEED-V (5 classes)
datasets show consistent improvements: best case up to +5.42% accuracy and 39% reduction in psychologically implausible misclassifications. Ultimately, our framework help raise the upper bound of performance achievable with standard approaches. Code will be released.
Read the full abstract ▾
All authors Dongyang Kuang, Zizheng Ma, Yushan Zhang, Xiaocong Zeng
Artificial Intelligence · Cross-listed from cs.LG
Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms
Ezgi Korkmaz
Starting from the utilization of deep neural networks to approximate the state-action value function that led to winning one of the most challenging games, to algorithmic advancements that allowed solving problems without even explicitly stating the rules of the challenge at hand, reinforcement learning research has been the center of remarkable scientific progress for the past decade. In this paper, we focus on the key ingredients of this research progress and we analyze the canonical evaluation and design paradigms in reinforcement learning. We introduce the theoretical foundations of scaling laws in reinforcement learning and show that the asymptotic performance of reinforcement learning
algorithms does not have a monotone relationship between performance rankings and data-regimes. We conduct large-scale experiments and our results demonstrate that a line of reinforcement learning research under the canonical design and evaluation paradigms resulted in incorrect conclusions. Our analysis and results provide a core analysis on scaling, capacity and complexity of deep reinforcement learning.
Read the full abstract ▾
Artificial Intelligence
Alignment Plausibility: A New Standard for Assuring AI in Healthcare
Gwydion Williams, Sara Zannone and Bilal A Mateen
Large
language models (LLMs) have become significant providers of mental health support, yet they remain products of an
attention economy whose operational and commercial targets favour sustained engagement over the friction that effective psychological support often requires. Developers' safety responses have been largely reactive, addressing the most visible and acute harms while subtler, longer-term patterns of risk (e.g., dependency, boundary erosion, the amplification of distorted beliefs) receive less
attention. We contend that making LLMs structurally safe requires
alignment organised at three levels that mirror how society assures the safety of human clinical practice: 1) explicit value specification grounded in the codified normative commitments of clinical practice; 2) training that embeds those values in the model; and 3) oversight that detects drift and longer-term harm during deployment, much as clinical supervision does for human practice. Organising
alignment in this way yields a construct we call
alignment plausibility - a structured demonstration that a system's values, training regime, and oversight mechanisms are together consistent with safe and positive outcomes. We propose
alignment plausibility as a regulatory construct (by drawing analogy to the established construct of biological plausibility) for AI in health: a principled way to argue for, or against, trust that systems are aligned to positive health outcomes, will cause no harm even where capable of doing so, and will ultimately lead to patient benefit.
Read the full abstract ▾
Artificial Intelligence
Aligning Clinical Needs and AI Capabilities: A Survey on LLMs for Medical Reasoning
Qi Peng, Jiatong Li, Sirui Huang et al. (+10 more)
Large
language models (LLMs) have emerged as important tools in healthcare, showing growing potential for clinical
reasoning and patient care. This survey examines recent progress in medical LLMs, focusing on
reasoning applications and requirements. We present a dual-view approach that connects clinical practice with computational methods. On the clinical side, we establish a five-level competency scheme following Miller's Pyramid, progressing from knowledge recall to dynamic case management. On the computational side, we link deductive, inductive, and abductive
reasoning patterns to common medical goals and tasks. We also introduce a
benchmark dataset spanning five levels of medical
reasoning capability and report results on 18 state-of-the-art models, revealing that medical specialist models excel in diagnosis-centric tasks while general models lead in decision support and dialogue. We conclude by discussing current progress and open challenges, including data limitations,
hallucination, and grounding issues, and outline directions toward safer, more reliable, and workflow-ready systems.
Read the full abstract ▾
All authors Qi Peng, Jiatong Li, Sirui Huang, Yiyang Jiang, Kaisong Gong, Ronger Ding, Shijie Ye, Changmeng Zheng, Yi Cai, Xiaobo Yang, Jin Huang, Xiao-Yong Wei, Qing Li
Artificial Intelligence
Adversarial Social Epistemology for Assemblies of Humans and Large Language Models
Mihnea C. Moldoveanu and Joel A.C. Baum
We outline an
adversarial social epistemology (ASE) for densely interactive communicative landscapes in which public assertions are scaffolded by chains of testimony, inference, institutional certification, and tacit trust. In such landscapes,
agents have incentives and affordances to distort, color, omit, fabricate, or strategically under-specify information for private, reputational, rhetorical, or material gains. We argue that these phenomena are not adequately captured by familiar descriptions of epistemic bubbles, echo chambers, or misinformation
diffusion. What requires explanation is how communicative
agents exploit the commitments and entitlements that normally make scaffolded assertions trustworthy. We provide
language that delivers the requisite analysis, outline mechanisms that subvert trust in scaffolded public communications, and outline machinery for
auditing and redressing trust breaches arising from subverting the auditability of inferential chains, drawing on epistemic networks, enriched with an inferentialist semantics for interpreting assertions.
Read the full abstract ▾
Artificial Intelligence
AI-integrated models for assessing agricultural resilience
Joshua R. Waite, Dana Golden, Brett Indelicato et al. (+8 more)
Agricultural supply chains are vulnerable to disruptions through linked biophysical and economic systems. We develop an AI-powered tool that integrates economic models (GTAP) with biophysical models (APSIM) to analyze supply chain shocks, enabling policymakers and
market participants to assess cross-disciplinary impacts through queries and responses written in natural
language.
Read the full abstract ▾
All authors Joshua R. Waite, Dana Golden, Brett Indelicato, Kevin Camp, Mojdeh Saadati, Shannon Regan, Patrick Schnable, Baskar Ganapathysubramanian, Carlos Messina, Suzanne Thornsbury, Soumik Sarkar
Artificial Intelligence · Cross-listed from cs.LG
A Transdiagnostic Space of Disorder Like Phenotypes in Reinforcement Learning Agents
Hari Prasad
Modelling psychological disorders in artificial
agents offers a testbed for computational psychiatry and a lens on affective-control failure modes. Prior work induces one or two disorders by hand-tuned reward shaping, labels the behaviour post hoc, and reports single runs. We recast disorder modelling as dose-controllable manipulation of cognitive appraisal signals in an appraisal-guided PPO
agent, expressing seven disorders (anxiety, mania, obsessive-compulsive checking, depression, impulsivity, addiction, and post-traumatic stress) each as a single knob grounded in a computational psychiatry account, with each symptom measured by a preregistered assay. Across more than a thousand runs (10 seeds, four controls, 95% confidence intervals) every disorder shows a graded, monotone dose-response that no control reproduces. Beyond these induced effects, three findings emerge that were not written into the reward: disorders self-organise into a two-dimensional affective space in which mania mirrors anxiety; removing a knob remits reward-distortion disorders (mania, checking, addiction) but not avoidance disorders (anxiety, PTSD), which recover under a graded exposure curriculum; and two simultaneous knobs interact nonadditively, yielding testable comorbidity predictions. The depression and addiction knobs further reproduce their double dissociation in a 3D pixel environment (MiniWorld) with a standard convolutional
agent and no appraisal critic, showing the framework generalises beyond grid worlds.
Read the full abstract ▾