Artificial Intelligence
A neural network that maintains and retrieves memories based on context
Hayoung Song, JeongJun Park, Qihong Lu et al. (+4 more)
Every day, people continuously infer situational context and adjust the way they understand and remember the world. Context, signaled by the prefrontal cortex, is known to modulate working
memory and episodic
memory, but the algorithmic understanding of this modulation remains limited. Here, we train a recurrent neural network (RNN), augmented with an episodic
memory buffer, to infer context using
Bayesian inference as it continuously makes predictions of upcoming scenes while watching naturalistic movies. When the inferred context modulates the RNN's recurrent connectivity (the basis of working
memory) in a low-rank manner, the model's activity patterns best match neural responses in human participants who watched the same movies during fMRI. Context also modulates episodic
memory retrieval, such that the model retrieves
memories based on not only content similarity but also context similarity. This is implemented as a key-value system with self-
attention, designed to additionally encode context and retrieve context-congruent
memories. The resulting model not only better resembles human
brain representations but also learns to retrieve
memories like humans much faster than a model without context modulation. Together, our findings suggest a computational mechanism by which context modulates information maintenance and long-term
memory retrieval in naturalistic environments.
Read the full abstract ▾
All authors Hayoung Song, JeongJun Park, Qihong Lu, Giacomo Vedovati, Monica D. Rosenberg, Zachariah M. Reagh, ShiNung Ching
Artificial Intelligence · Cross-listed from cs.LG
Predictive Self-Supervised Learning Provably Identifies Stochastic Signals under Nuisance
Fabian A. Mikulasch and Friedemann Zenke
Self-supervised learning (SSL) by predicting in latent space, without generating the input data itself, learns highly abstract, useful representations. Intuitively, this success is often attributed to its ability to discard nuisance information that is irrelevant to prediction. However, this poses a conundrum: both
stochastic variation in a prediction-relevant latent signal and true nuisance make observations partly unpredictable; how could they be distinguished? Surprisingly, we prove that common SSL methods can achieve exactly this, by implicitly instantiating a latent-variable model with
stochastic dynamics and observation-private nuisance. We trace their ability to recover the
stochastic signal to two complementary principles: Predictive mutual information maximization ensures that representations retain the information needed for prediction, while latent distribution matching constrains how this information is encoded, thereby making the retained signal identifiable. We confirm this identifiability result in simulations for Gaussian predictors, which recover the true signal up to an affine transformation even in dynamic, nuisance-laden environments.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
A Proposed Rubric for Evaluating Expressed Clinical Reasoning in Large Language Model Responses
Zhangshu Joshua Jiang, Zina Ibrahim and James T. Teo
We propose a rubric for assessing expressed clinical
reasoning in model responses, drawing on three bodies of work: medical education assessment frameworks (ART, SCT, Key Feature Problems and OSCE); clinical LLM
benchmarks (MedR-Bench, HealthBench, TIMER-Bench, DR. BENCH,
PrIME-LLM and PatientSafeBench); and general LLM
reasoning evaluation research, including the Factuality-Validity-Coherence-Utility taxonomy, FaithCoT-Bench and C2-Faith. We use groundedness as a clinically oriented adaptation of the taxonomy's factuality category. The rubric brings these concepts together in a multidimensional framework for scoring free-text responses to gold-standard clinical vignettes. It includes provisional behavioural anchors, applicability rules and a separate flag for case-specific safety-critical errors. General-domain frameworks inform its design but are not treated as validated clinical instruments. The rubric does not replace case-specific reference criteria or the task-specific metrics of existing
benchmarks. It has not yet been tested for inter-rater reliability, construct validity or clinical utility. Its immediate purpose is to make evaluation decisions explicit and open to scrutiny before empirical testing.
Read the full abstract ▾
Artificial Intelligence
Adam under Generalized Smoothness with Second-Moment-Type Stochastic Gradients
Ruinan Jin, Difei Cheng, Ling Chen et al. (+3 more)
Adam is widely observed to remain stable even when the objective deviates significantly from global smoothness. Under the generalized smoothness framework, however, existing analyses rely on strong tail assumptions on the
stochastic gradients, such as almost-sure boundedness or sub-Gaussianity. Whether Adam converges on generalized smooth objectives under only second moment information on the
stochastic gradients, without such concentration assumptions, was identified as an important open direction by Li et al. (2023). This paper gives an affirmative answer under fairly general conditions: such tail assumptions are not necessary. Building on the Adam self-normalization framework of Jin et al. (2026), developed for classical smoothness and bounded variance, we extend the stopping-time and de-preconditioning strategy to the $L_0$-$L_p$ generalized smoothness condition and a generalized second moment ABC condition. Even when the
stochastic-gradient condition provides only second moment information that may grow along the trajectory, the
stochastic trajectory of Adam remains in a locally well-behaved smoothness region, with stretched-exponential tail decay under bounded variance and global smoothness. Consequently, we establish high-probability convergence rate guarantees over the full range $p<2$, with confidence dependence of order $\delta^{-1/2}$, while the stepsize prefactor depends on $\delta$ only through a single logarithmic factor. We further construct a hard instance showing that, under only second-moment information, this $\delta^{-1/2}$-type confidence dependence is sharp. Finally, in the regime $p<1$, we combine the trajectory control with
polynomial-growth estimates on rare events to obtain convergence rate guarantees in expectation.
Read the full abstract ▾
All authors Ruinan Jin, Difei Cheng, Ling Chen, Jun Luo, Hao Zhou, Youzhi Zhang
Artificial Intelligence · Cross-listed from cs.CV
A Benchmark & Dataset for Detecting AI-Manipulated Visual Evidence in the Court System
Kelly McConvey, Sajad Ebrahimi, Nima Jamali et al. (+10 more)
Photographic evidence is becoming increasingly vulnerable to forms of alteration and fabrication that existing legal and technical workflows are not well equipped to evaluate. Surveillance frames, dashcam stills, and phone photographs may be used to establish presence, sequence, causation, damage, or identity, yet contemporary generative systems allow non-experts to alter or fabricate such images through ordinary
prompt-based interfaces. Existing image-forensics
benchmarks provide important resources for face manipulation, classical tampering, and general synthetic-image detection, but they are not organized around the forms of visual evidence submitted in courts, the localized edits that can change what an exhibit appears to prove, or the consumer-tool threat model now facing the justice system. We introduce the CIFAR Synthetic Evidence Corpus for Detecting AI-Manipulated Images, a
benchmark for evidentiary image authentication in court and justice-system contexts. The corpus contains 1,505 photographic items, including 720 authentic controls and 785 manipulated or fabricated images, spanning surveillance, dashcam, and consumer-photo imagery. Manipulations are organized into scene-condition edits, localized element edits, and full fabrications produced with contemporary generative systems. Each item is released with structured metadata covering source provenance, manipulation tier, subtype, generator,
prompt template, and scene attributes, enabling controlled evaluation beyond aggregate binary detection. We also establish baselines with publicly available image-manipulation detectors, showing that current systems exhibit error profiles that remain problematic for evidentiary use. The
dataset,
prompts, metadata, code, and baseline evaluation scripts are released to support research on visual evidence authentication, information integrity, and trustworthy AI for the justice system.
Read the full abstract ▾
All authors Kelly McConvey, Sajad Ebrahimi, Nima Jamali, Jalehsadat Mahdavimoghaddam, Matina Mahdizadeh Sani, Maksym Taranukhin, Wentao Zhang, Jacquelyn Burkell, Yuntian Deng, Karen Eltis, Maura R. Grossman, Vered Shwartz, Ebrahim Bagheri
Artificial Intelligence · Cross-listed from cs.CV
HiRAE: Hierarchical Representation Autoencoding with Residual Budgets
Xuanyu Zhu, Yan Bai, Yang Shi et al. (+5 more)
Pretrained visual representations support image generation, but may not fully preserve the fine-grained details needed for faithful reconstruction. Meanwhile, intermediate encoder layers contain complementary visual details, but learning to fuse them for reconstruction can produce a latent distribution that is difficult to model. Existing fusion methods require empirical tuning of layer selection or staged optimization of fusion and decoding, increasing configuration effort or training complexity. We introduce HiRAE (Hierarchical Representation Autoencoder), which learns a hierarchical fusion framework over the full encoder hierarchy to improve reconstruction fidelity while maintaining compatibility with generative modeling. HiRAE groups encoder layers by depth and learns residual corrections to the deepest representation. Group-wise norm caps bound these corrections relative to the deep anchor, with tighter budgets for shallower groups. Our HiRAE-24 preserves the latent
token count and channel dimension. On ImageNet-256, HiRAE-24 reduces reconstruction FID from 0.299 to 0.209 relative to RAEv2 while maintaining competitive guided generation quality. For text-to-image generation, HiRAE-24 improves
alignment over RAEv2 on GenEval, DPG-Bench, and GenAI-Bench both before and after supervised fine-tuning. Under the same generator-training and evaluation protocol, post-fine-tuning GenEval increases from 84.86 to 87.70.
Read the full abstract ▾
All authors Xuanyu Zhu, Yan Bai, Yang Shi, Yihang Lou, Yuanxing Zhang, Tengfei Liu, Jing Jin, Yuan Zhou
Artificial Intelligence
OmniVCBench: Benchmarking Evidence-Grounded Multimodal Reasoning Towards AI Virtual Cells
Manyu Li, Xunkai Li, Yongfu Xiong et al. (+3 more)
Artificial Intelligence Virtual
Cells (AIVCs) are envisioned as scientific
agents that simulate cellular responses, explain underlying mechanisms, and support hypothesis-driven discovery. Existing AIVC
benchmarks, however, operate primarily at the simulation layer, motivating complementary evaluation of how models interpret experimental evidence and formulate biological hypotheses. We introduce OmniVCBench, a figure-centric, source-traceable
benchmark for the interpretation component of an AIVC. It contains 6,077 curated single- and multi-subfigure question–answer pairs derived from figures and experimental contexts in the scientific literature. Guided by Bloom's taxonomy, we instantiate interpretation-layer counterparts of the AIVC Predict–Explain–Discover agenda through three scientific
reasoning tasks. We further introduce AIVC-Judge, a task-conditioned MLLM-as-a-judge framework with category-specific, reference-aware rubrics for evaluating open-ended responses. A complementary Model-Derived Hard-Negative Mining (MDHNM) strategy converts plausible errors observed during model inference into MCQ distractors for lower-cost evaluation. Within the evaluated heterogeneous model pool, MCQ accuracy correlates positively with AIVC-Judge scores, providing a complementary view of performance alongside open-response evaluation. Code and data demo are available at https://anonymous.4open.science/r/OmniVCBench.
Read the full abstract ▾
All authors Manyu Li, Xunkai Li, Yongfu Xiong, Yi Liu, Rong-Hua Li, Guoren Wang
Artificial Intelligence
Cross-Entropy Guided Routing in Mixture-of-Experts Large Language Models
Yury Nahshan, Nati Daniel, Jacob Goldberger et al. (+1 more)
Sparse mixture-of-experts (MoE) large
language models scale model capacity by routing each
token to a small subset of experts. Their routers are regularized with load balancing terms and learn affinity scores through the
language-model objective. However, these objectives do not provide direct
alignment between routing affinities and
token-level error. We introduce
token-error supervision for sparse routing in two forms. The first form predicts an error score per expert. The affinity-weighted aggregate of these scores is aligned to the next-
token cross-
entropy loss, while the individual scores attenuate affinity before top-$K$ selection. The second directly aligns the router's affinities to the model's objective without requiring an additional head or inference-time modification. Both formulations use the Itakura–Saito divergence or an exponential negative log-likelihood for aligning affinities and
token errors. Across two sparse MoE backbones and four multiple-choice question-answering
benchmarks, we evaluate both supervision mechanisms. On Granite, our method improves accuracy by approximately 2.3 percentage points on average over a parameter-matched routing baseline. With stronger supervision, the gain on ARC-Challenge reaches 2.94 points. Both mechanisms preserve the native sparse execution budget and aggregation policy. Our code is available in the supplementary materials.
Read the full abstract ▾
All authors Yury Nahshan, Nati Daniel, Jacob Goldberger, Yoli Shavit
Artificial Intelligence · Cross-listed from cs.CV
Multi-Site Real-World Performance of Commercial AI for Pulmonary and Incidental Pulmonary Embolism Detection
Aawez Mansuri, Mohammadreza Chavoshi, Theodorus Dapamede et al. (+13 more)
Pulmonary embolism (PE) is a leading cause of cardiovascular mortality, yet the real-world performance of FDA-cleared AI detection models remains incompletely characterized. We retrospectively evaluated two FDA-cleared AI
algorithms from a single commercial platform (Aidoc Medical BriefCase), one for PE triage on dedicated CT pulmonary angiography (CTPA; n = 30,678) and one for incidental PE (iPE) detection on routine contrast-enhanced CTs (n = 37,191), across a 17-facility academic health system. Reference-standard labels were extracted from radiology reports using a validated LLM pipeline (97% accuracy, kappa = 0.94). The PE model achieved 86.8% sensitivity and 99.1% specificity, with sensitivity declining from 99.3% for saddle emboli to 72.9% for subsegmental PE, and from 89.7% for acute to 65.3% for non-acute PE. The iPE model achieved 73.5% sensitivity and 99.8% specificity. Both models demonstrated lower sensitivity than FDA-clearance
benchmarks while exceeding cleared specificity, with diminishing performance for peripheral and non-acute emboli mirroring known human reader limitations and underscoring the need for standardized post-
market surveillance of AI-enabled medical devices.
Read the full abstract ▾
All authors Aawez Mansuri, Mohammadreza Chavoshi, Theodorus Dapamede, Wasif Bala, Beatrice Brown-Mulry, Rohan Isaac, Bardia Khosravi, Hanzhou Li, Frank Li, John T. Moon, Chad Robichaux, Dan I.G. Cohen-Addad, Ninad V. Salastekar, Janice Newsome, Judy W. Gichoya, Hari Trivedi
Artificial Intelligence
ContextRender: From Execution Dependencies to Agent Context
Savini Kashmira, Jayanaka L. Dantanarayana, Lingjia Tang et al. (+1 more)
LLM
agents performing long-horizon tasks accumulate tool results that later steps may need. Passing the full history to every invocation is costly even when it fits within the context window, while reducing it risks omitting needed information. Existing context management methods can overlook how earlier tool results are used in subsequent execution, leaving needed information out of context. We introduce ContextRender, which manages context through a persistent graph of execution dependencies. We develop Tool-Flow Analysis to track how later operations reuse information from earlier tool results, providing a signal called observed reuse. A renderer combines this signal with recency and semantic relevance to select results within a fixed history budget, retaining omitted results for later use. Across AppWorld and 8-objective QA with three execution models, ContextRender outperforms the evaluated context management baselines using a 6K history budget, well below the models' maximum context windows. Within this budget, it achieves task performance close to or above that of passing the full history while reducing mean inference cost by 10.2%-32.2% relative to Full history. Ablations show that observed reuse improves task performance and retention of results reused later.
Read the full abstract ▾
All authors Savini Kashmira, Jayanaka L. Dantanarayana, Lingjia Tang, Jason Mars
Artificial Intelligence
Spatiotemporal Hyperedges for EEG Seizure Detection and Prediction
Hyunju Kim, Sheo Yon Jhin, Noseong Park et al. (+1 more)
Seizure detection and prediction from
EEG are clinically important but challenging because seizures are rare, temporally localized, and propagate as coordinated events across multiple channels. Recent dynamic graph neural networks model this by running a temporal model over a sequence of per-time-step pairwise channel edges. However, this pairwise construction misses the spatiotemporal coupling that constitutes a seizure, at substantial training cost. We propose HyBrain, which summarizes spatiotemporal
EEG evidence through a small set of soft hyperedges rather than pairwise edges. A per-channel Mamba backbone produces one
token per (channel, second), and a spatiotemporal hyperedge block pools these
tokens into E_h shared group
embeddings through soft memberships and broadcasts them back. The same encoder serves three downstream tasks: window-based detection, one-second point-wise detection, and preictal seizure prediction. On TUSZ and CHB-MIT, HyBrain achieves the best AUROC on every reported setting against ten baselines, with the largest gap on long-clip preictal prediction. It also matches the most efficient baselines in training time and peak GPU
memory. A qualitative analysis shows that even a single learned hyperedge cleanly captures the preictal -> ictal -> postictal trajectory on a real seizure clip.
Read the full abstract ▾
All authors Hyunju Kim, Sheo Yon Jhin, Noseong Park, Nabil Imam
Artificial Intelligence
Rulin Shao, Shannon Zejiang Shen, Junjie Oscar Yin et al. (+10 more)
We introduce Context
Language Models (CLMs),
language models that natively manage their own context. We implement this by treating the context as a file and allowing the model to make unrestricted updates to this file. This allows the model to learn what is most important to maintain in context, and naturally extends to multi-
agent systems where multiple
agent contexts coexist as files. Building CLMs zero-shot with existing models outperforms SOTA context management strategies across a variety of tasks: 11.4% higher accuracy with 21.5% fewer FLOPs on BrowseComp-Plus, 5% higher scores with 59% fewer FLOPs on 12-hour EdgeBench, and 65% greater improvement with the same compute on a 24-hour multi-repository
agent-swarm task. Moreover, by shifting context management from external harness control to intrinsic model behavior, CLMs naturally enable both in-context and parametric learning of context-management strategies. We show that CLMs can be steered with natural-
language instructions evolved through a standard skill-optimization loop, improving held-out accuracy by up to 35.9 points on a context-management task while reducing compute. We also introduce an online reinforcement learning method for CLMs, improving Qwen3.5-9B performance on BrowseComp-Plus by 47.6% while using 12% fewer FLOPs. Finally, we co-design Suffix Cache Reuse for CLM serving, further reducing server-side compute by 35% relative to standard SGLang at matched performance.
Read the full abstract ▾
All authors Rulin Shao, Shannon Zejiang Shen, Junjie Oscar Yin, Yuetai Li, Minheng Wang, Hamish Ivison, Radha Poovendran, Nathan Lambert, Teng Xiao, Mike Lewis, Wen-tau Yih, Luke Zettlemoyer, Pang Wei Koh
Artificial Intelligence · Cross-listed from cs.CV
PolyOCR-Venus: Unified OCR Foundation Models for Text-Centric Visual Intelligence
GuangJian Team: Kaili Huang, Yongshuo Zhang, Bingtao Fu et al. (+21 more)
Optical Character Recognition (OCR) is evolving from plain-text transcription toward general visual intelligence, requiring models to recognize, localize, and reason over textual information in complex visual environments. However, existing OCR systems often excel at only some tasks and struggle to balance recognition, parsing, and
reasoning across scenarios. In this report, we present PolyOCR, a family of unified OCR foundation models of varying scales. PolyOCR combines a shared instruction-following framework with a large-scale data engine that converts heterogeneous visual resources into quality-verified OCR supervision. We introduce Competence-Guided Policy Optimization, which combines verifier-based Group Relative Policy Optimization with on-policy
distillation through sample-wise routing based on teacher reliability and the teacher–student competence gap. We also introduce OCRBench v2.1, our revision of OCRBench v2 with manually verified annotation corrections and task-aligned scoring metrics. Extensive experiments across OCRBench v2.1, CC-OCR, in-house KIE
Benchmark, OmniDocBench v1.6 and MDPBench demonstrate that PolyOCR achieves state-of-the-art or highly competitive performance.
Read the full abstract ▾
All authors GuangJian Team: Kaili Huang, Yongshuo Zhang, Bingtao Fu, Changjiang Jiang, Chenfan Qu, Chenfeng Zhang, Fangming Cui, Gaoyang Zhang, Jiangwei Xie, Jianshu Li, Jing Huang, Jingwen Bai, Mingqi Fang, Tao Fang, Weihong Zhang, Wenbo Du, Xiongfei Bai, Xuekang Zhu, Yinan Xia, Zhenming Wang, Jian Liu, Jingjing Liu, Xiang Qi, Weiqiang Wang
Artificial Intelligence · Cross-listed from cs.CV
VIF-Bench: Evaluating Visual Instruction Following in Multi-Reference Image Generation
Yuta Oshima, Masakazu Yoshimura, Masahiro Suzuki et al. (+2 more)
Recent
multimodal image generation models can take multiple images and textual instructions as input, enabling reference-based generation guided not only by text but also by visual instructions such as layouts, arrows, and pose cues. However, existing
benchmarks do not evaluate the joint setting in which multiple references must be composed under multiple and heterogeneous visual-instruction images. To address this gap, we introduce VIF-Bench, a
benchmark of 1,241 tasks designed to assess the edge of model capabilities in this joint setting by covering: (i) multi-reference generation (up to 7) under multiple heterogeneous visual instructions (up to 6), (ii) cases where reference images can potentially compete with visual instructions (e.g., a strongly posed subject vs. a target pose), and (iii) controlled comparison of visual instructions with text descriptions at different levels of specificity. Using these capabilities, we uncover three findings: (1) models face an adherence-artifact trade-off: once models reach stronger visual instruction adherence, stronger adherence tends to coincide with more instruction artifacts in generated images, (2) visual instruction adherence tends to be lower on tasks whose reference images carry a salient state of the controlled attribute (e.g., a neon-lit subject under a light-direction instruction), most consistently for light and wind, and (3) for models that can understand visual instructions, it is often better to provide visual constraints directly rather than describe them in text; when using text, a moderate level of detail works better than an exhaustive description. VIF-Bench is released as an open
benchmark to establish a basis for fair comparison in controllable multi-reference image generation.
Read the full abstract ▾
All authors Yuta Oshima, Masakazu Yoshimura, Masahiro Suzuki, Yutaka Matsuo, Hiroki Furuta
Artificial Intelligence
Generative Interactions: Weaving Multiparty Human Motion with Bilevel Latent Dynamics
Ojas Shirekar, Yash Surange, Agustinas Jučas et al. (+1 more)
Human social behaviour is not a collection of independent motions, but a jointly organised process in which group dynamics and individual variation continuously shape one another. Yet existing social motion models often prioritise plausible trajectories while leaving interaction state implicit, limiting their ability to transfer across groups, tasks, and partial-observation regimes. To address this gap, we introduce Bilevel Representations for
Agent Interaction Dynamics (BRAID), a hierarchical sequential latent-variable model for generative multi-person interaction. BRAID explicitly formulates social motion generation as a meta-transfer learning problem: shared interaction priors are learned across
datasets and adapted through arbitrary context sets of observed people and joints. The model represents each scene through a group-level latent state that captures shared interaction dynamics and person-level latent states that capture individual behaviour conditioned on the evolving group context. This modelling choice enables coherent generation under full, sparse, or partial observations while exposing compact social-state vectors that can serve as an interface for downstream
embodied-
agent systems. We evaluate BRAID under a unified SMPL-based representation on social
forecasting, tracking and in-filling, and response generation, using metrics that assess not only reconstruction accuracy but also realism, diversity, temporal
alignment, and interpersonal coordination. We further analyse the hierarchical latent space, showing that it captures separable group- and individual-level structure.
Read the full abstract ▾
All authors Ojas Shirekar, Yash Surange, Agustinas Jučas, Chirag Raman
Artificial Intelligence · Cross-listed from cs.LG
Width Expansion as a Method for Class Incremental Learning
A. L. S. Conde, Y. Elkhatib and C. M. Ranieri
Class Incremental Learning (Class-IL) requires models to learn new classes over time while preserving previously acquired knowledge without access to past data or task identity. This setting intensifies the stability-plasticity dilemma and makes catastrophic forgetting a central challenge. Existing approaches include regularization, knowledge
distillation, replay, and architectural expansion. However, many expansion methods rely on explicit task identifiers or predefined growth strategies, limiting their applicability when task boundaries are unavailable at inference time. This work proposes a dynamic width expansion method that increases the number of
neurons within existing layers according to a normalized loss criterion, without requiring task-specific information. An
attention mechanism with persistent key-value
memory is also incorporated to stabilize feature representations and reduce interference between previously learned and newly introduced classes. The approach is evaluated on Split MNIST and Split CIFAR-100 under the standard Class-IL protocol. Experiments compare fixed-capacity and dynamically expanding architectures, both with and without
attention, combined with established continual learning methods including EWC, LwF, and A-GEM. Results show that progressive width expansion consistently improves performance over fixed architectures, particularly when combined with functional methods and A-GEM. The combination of width expansion and
attention provides the most consistent gains. Overall, dynamic width expansion based on representational demand provides an effective and flexible strategy for Class-IL, although uncontrolled growth may increase overfitting and computational cost.
Read the full abstract ▾
Artificial Intelligence
Locating Answer-Correctness Signals in Frozen Large Language Models
Yuansen Liu, Yixuan Tang and Anthony Kum Hoe Tung
Language models expose internal signals that predict whether an answer is correct, readable from a single forward pass of a frozen model without additional generations. Yet existing probes often commit to one signal family or layer and can be brittle under distribution shift; in
retrieval-augmented settings, many specialized detectors instead target passage faithfulness, which can diverge from correctness when retrieved evidence is unhelpful or conflicting. We therefore ask where answer correctness is readable, which internal signal families carry it, and how they should be combined. We search over hidden states,
token probabilities, residual-stream features,
attention, and their fusion, treating the selected readouts as a predictive measurement rather than a mechanistic localization. We run this analysis separately in closed-book and with-context settings, since context can change which readouts are informative. A consistent anatomy emerges: correctness concentrates in the answer span, recovered from the answer
tokens even under
retrieval, and the families carry it complementarily, so fusing them helps most out of distribution, where a single signal is weakest. The protocol is effective across two backbones and gates a
retrieval controller as one downstream use.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
GARDiff: Graph-Aligned Residual Diffusion for Probabilistic Multivariate Time-Series Forecasting
Rui Han, Min Yang, Xu Zhang et al. (+3 more)
Diffusion models have recently shown strong potential for probabilistic multivariate time-series
forecasting by modeling complex conditional distributions. Recent decoupled
diffusion frameworks further separate
forecasting into deterministic prediction and
stochastic residual generation, making it natural to derive dependency graphs from deterministic representations and use them to guide residual
diffusion. However, we show that this direct structural transfer is unreliable. Although deterministic-derived graphs encode useful global dependency priors, they exhibit substantial edge-level misalignment with residual dependency structures, introducing inaccurate or redundant conditions during residual generation. This reveals a previously overlooked deterministic-to-residual structural
alignment problem in decoupled
diffusion forecasting. To address this problem, we propose GARDiff, a Graph-Aligned Residual
Diffusion framework for probabilistic multivariate time-series
forecasting. Instead of treating deterministic-derived graphs as fixed
diffusion conditions, GARDiff progressively adapts them to residual generation. Specifically, GARDiff estimates residual uncertainty to distinguish high- and low-uncertainty regions, enabling uncertainty-aware structural refinement, and further performs timestep-aware edge sparsification during reverse
diffusion to evolve graph conditions from broad dependency aggregation to localized residual refinement. Extensive experiments on six real-world
benchmarks demonstrate that GARDiff consistently improves probabilistic
forecasting performance and uncertainty calibration over strong baselines.
Read the full abstract ▾
All authors Rui Han, Min Yang, Xu Zhang, Xinghao Yang, Wei Liu, Yongshun Gong
Artificial Intelligence
WISE-ATTA: When to Ask for Labels in Budgeted Active Test-Time Adaptation
Muhammad Huzaifa, Lea Schönherr and Thorsten Eisenhofer
Active test-time adaptation (ATTA) improves robustness under distribution shift by updating a deployed model during inference while selectively querying supervision. However, most existing ATTA methods implicitly assume that supervision can be requested for every incoming test batch, which can incur substantial annotation cost over long test streams. In this work, we introduce budgeted ATTA in which labels are available for only a fraction of test batches. This formulation shifts the central challenge from deciding what to label within a batch to deciding when supervision should be applied over time. To address this challenge, we propose a budget-aware approach WISE-ATTA that allocates supervision over the test stream based on lightweight signals computed online, prioritizing periods where supervision is likely to be most useful. When a batch is selected for supervision, we further employ a drift-based sample selection criterion that targets samples exhibiting ongoing, unconverged adaptation dynamics, enabling effective updates from a single labeled example. We evaluate this approach on synthetic corruptions (ImageNet-C) and natural distribution shifts (ImageNet-R/K/A). Across settings, WISE-ATTA achieves competitive or improved performance compared to recent ATTA methods while requiring substantially fewer labels. Overall, we find that the timing of supervision is a key, yet underexplored, aspect of active test-time adaptation. Code: https://github.com/Muhammad-Huzaifaa/WISE-ATTA
Read the full abstract ▾
Artificial Intelligence
EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments?
Hongcheng Gao, Hailong Qu, Yu Lei et al. (+19 more)
Autonomous
agents have made rapid progress in general-purpose computer use, yet reliable automation of professional industrial engineering remains out of reach. Engineering workflows require
reasoning over
geometric and physical constraints and keeping dependencies consistent across software and design stages. We present EngiWorld, a
benchmark designed around the capabilities that real engineering projects require, from operating a single application to solving engineering problems end to end. It contains 1,301 expert-curated tasks spanning six engineering domains (CAD, CAE, CAM, BIM, EDA, and DCC) and 26 professional software applications, with both GUI and CLI interfaces. The tasks are organized into six types, corresponding to capabilities that real engineering projects require. We further introduce an artifact-centric evaluation methodology built on a unified suite of domain verifiers. The verifiers programmatically check whether final and intermediate artifacts are geometrically valid, physically feasible, and compliant with design rules. Beyond binary success, they also score how well optimized designs meet their specifications. Evaluation of seven frontier models reveals a substantial capability gap: the strongest model scores only 44.7/100, and just 3.6% of runs on tasks that require cross-software coordination succeed. EngiWorld provides a rigorous foundation for measuring progress toward
agents that operate professional engineering software end to end.
Read the full abstract ▾
All authors Hongcheng Gao, Hailong Qu, Yu Lei, Henghui Sun, Haoyang Li, Yipeng Wei, Naihao Xue, Xiaohan Yu, Zhuo Tao, Yihe Zang, Yajiao Wang, Jingyi Tang, Yi Li, Jingjing Zhou, Jie Luo, Bohan Zeng, Chengyu Shen, Hao Jiang, Chong Chen, Bowen Qu, Olive Huang, Zeqiang Wang
Artificial Intelligence
Learning from Shared-Control Overrides: Context-Driven Acceleration Profile Prediction for Personalized Overtaking
Ruizheng Xu, Lounis Adouane, Javier Ibañez-Guzmán et al. (+1 more)
Adaptive Cruise Control (ACC) systems are typically calibrated for an average driver, often resulting in a mismatch between vehicle behavior and individual expectations during time-critical maneuvers such as highway overtaking. When the ACC is perceived as too conservative and inconsistent, drivers intervene through throttle overrides, providing implicit feedback on the system's behavior. This paper reframes these override actions as human-in-theloop supervisory signals and proposes a data-driven framework for personalized vehicle adaptation, termed Context-driven Personalized ACC (CoP-ACC). Rather than relying solely on end-to-end regression, which tends to over-smooth dynamic responses, we introduce a hybrid pipeline combining: (i) unsupervised hierarchical clustering to extract representative acceleration profiles from override events; (ii) a context classifier that maps pre-maneuver driving conditions to the appropriate profile; and (iii) a residual regressor that refines the selected profile into a smooth, personalized acceleration profile tailored to the immediate context. Evaluated on real-world public-road data against a withheld forced-ACC baseline, the approach demonstrates high reconstruction fidelity and generates acceleration profiles that tend toward the driver's expected behavior in potential override contexts. The results highlight the potential of learning from shared-control overrides to enable anticipatory, personalized ACC behavior, reducing manual interventions and improving ride comfort.
Read the full abstract ▾
All authors Ruizheng Xu, Lounis Adouane, Javier Ibañez-Guzmán, Clément Zinoune
Artificial Intelligence · Cross-listed from cs.LG
When Models Don't Manipulate Manifolds: The Geometry of a Comparison Task
Sai Sumedh R. Hindupur, Hadas Orgad, Thomas Fel et al. (+1 more)
One of the current premises of mechanistic interpretability research is that detailed accounts of the geometry of neural network representations can tell us how models perform computations, and how to effectively intervene on them. While low dimensional
manifolds have been observed for multiple concepts in the literature (e.g. numbers encoded on helices, days of the week on a circle, ...), with structure believed to reflect properties of data and tasks, the extent to which models rely on them for computation, and how they manipulate them, remains unclear. We characterize precisely the geometry of computation in a number-comparison task, as an abstraction of comparison for decision making, and how models utilize geometry in an elegant fashion to implement it. Specifically, we study the causal geometry of number comparison in Qwen2.5-7B-Instruct, a capable and widely studied open-weight model, and find Qwen largely uses linear representations of numbers despite the presence of curved geometry. To compare two numbers, the model first encodes each number along a vector and adds the two representations using
attention and the residual connection, bringing them into a shared space in the residual stream. Then, the model uses MLP
neurons to compare the pair of numbers on local regions in this shared space, which correspond to smaller intervals of input numbers, and combines these to obtain the position of the maximum. In fact, this reliance on linear representations for comparison also persists when the model compares three numbers. Our findings demonstrate that the
manifold hypothesis can co-exist with linear representations: while concepts that are ordered may have
manifold structure in representations, the model may use an underlying linear structure of the concept in certain computations.
Read the full abstract ▾
All authors Sai Sumedh R. Hindupur, Hadas Orgad, Thomas Fel, Demba Ba
Artificial Intelligence
KUPAS MASTER: Distilling the Tacit Expertise of Master Practitioners into Agent-Ready Experience Corpora
Changmian Wang, Yuchao Ma, Xuchao Lu et al. (+13 more)
Experienced professionals know more than just facts and conclusions. They know which cues matter, why a judgment is reasonable, and which action to take. Routine work records often leave out this tacit knowledge, making it difficult for Large
Language Model (LLM)
agents to use professional experience effectively. We introduce KUPAS MASTER, an experience engineering platform built around nine-layer cognitive corpus construction. It turns heterogeneous work records and practitioner interviews into traceable, reusable experience corpora for
agents. Six case elements preserve the task process: context, cues, judgment, action, boundaries, and outcomes. Nine-layer cognitive corpus construction organizes tacit experience along nine extraction dimensions and stores the resulting assets in six libraries: rules, constraints, best practices, negative examples, corner cases, and skills. Semantic
alignment, individual experience
distillation, organizational consolidation, and cross-review preserve source evidence, conditions of use, and unresolved disagreements. The platform packages these assets into callable skills with explicit inputs, steps, dependencies, and stopping conditions, connecting experience collection to task execution and evaluation feedback. Using authorized samples from 20 randomly selected practitioners, the platform processed 1,576 source files into 23,024 individual experience records and 13,113 organizational assets. The evaluation spans multiple professional domains. Under common task inputs and scoring criteria, the base model, raw corpus
retrieval-augmented generation (RAG), and KUPAS MASTER
agent scored 70.63, 79.75, and 89.58, respectively. The KUPAS MASTER
agent improved on raw-corpus RAG in all seven scoring dimensions. The platform provides a practical path from individual tacit experience to organizational knowledge and
agent capabilities.
Read the full abstract ▾
All authors Changmian Wang, Yuchao Ma, Xuchao Lu, Chen Zhang, Ping Sun, Jiazheng Wang, Shan Wang, Xuanwen Chen, Yihe Sun, Ziyu Lu, Jianqiang Huang, Hongzhi Li, Ziqing Xia, Kaihua Tang, Xian-Sheng Hua, Qinghua Zheng
Artificial Intelligence
MeanFlowAdvantage: Stable Reward Fine-Tuning for Few-Step Average-Velocity Generators
Haocheng Tang, Tianchi Xie and Xingqiao Lin
MeanFlow enables efficient few-step generation by predicting interval-average velocities, but this representation creates a mismatch for reward fine-tuning: existing advantage-based objectives are typically defined on instantaneous velocities or equivalent $x_0$-space predictions, whereas inference directly uses the learned average-velocity map. We introduce MeanFlowAdvantage, a signed advantage-weighted least-squares objective for average-velocity generators. Our key construction uses a shared, detached MeanFlow derivative correction to express the reward objective in prediction space while making rollout and reference regularization exact penalties on the average-velocity network deployed at inference. The resulting formulation preserves MeanFlow's native few-step sampler and provides a direct mechanism for transferring reward improvements to the deployed flow map. On SD3.5-Medium, MeanFlowAdvantage improves all eight reported metrics over the matched four-step MeanFlowNFT baseline and, with only four NFEs, matches or exceeds the 40-step DiffusionNFT baseline on six of eight metrics. The same objective also transfers to DNA promoter design, where it supports both teacher-free on-policy RL for a generator defined on a
manifold and teacher-guided reward-graded
distillation, with the latter yielding the lowest one-step Sei profile MSE among the compared configurations.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
Retrieve, Reproduce, Reveal: Dissecting Retrieval-Augmented Software Vulnerability Detection
Sabrina Kaniewski, Tim Krämer, Julius Bächle et al. (+3 more)
Retrieval-Augmented Generation (RAG) is increasingly used to enhance Large
Language Model (LLM)-based software vulnerability detection by grounding predictions in retrieved vulnerability knowledge, such as vulnerability reports. However, existing RAG-based software vulnerability detection (RAG4SVD) systems are often evaluated using proprietary models, which challenges open science and reproducibility. Further, studies use different
datasets, custom knowledge bases, different backbone models, and diverse metrics, which hinders meaningful cross-system comparison. In this work, we study six open-source RAG4SVD systems and address these reproducibility and comparability challenges through (i) reproduction of their experimental settings under an open-weight setting, and (ii) a unified
benchmark using a common
dataset, metric suite, and pool of open-weight models. Further, RAG4SVD systems typically consist of multiple components, yet are often evaluated only as a whole system, i.e., end-to-end. Therefore, we perform (iii) a component-level analysis that decomposes representative RAG4SVD pipelines into input abstraction, knowledge
retrieval, and detection. Our results demonstrate that reproducibility varies substantially across systems. Under the presented unified
benchmark, published RAG4SVD performance does not transfer under a controlled open-weight evaluation and depends strongly on the used model. The component analysis shows that effective RAG4SVD depends on the
alignment between pipeline stages. For example, oracle knowledge raises
retrieval to near-optimal, yet performance remains low (0.51 pairwise accuracy), demonstrating that
retrieval effectiveness alone is insufficient for reliable detection. These findings motivate evaluating RAG4SVD not only end-to-end, but at the level of pipeline components, and provide a basis for more standardized, RAG-aware evaluation practices.
Read the full abstract ▾
All authors Sabrina Kaniewski, Tim Krämer, Julius Bächle, Markus Enzweiler, Michael Menth, Tobias Heer
Artificial Intelligence · Cross-listed from cs.RO
Semantic Map Sharing and Capability-Aware Coverage Planning for AI-Native 6G Robotic Coordination
Abdulqader Dhafer, Qi Wang and Zhou Daniel Hao
Search and Rescue (SAR) operations increasingly deploy heterogeneous teams of aerial and ground
robots. However, conventional coverage methods typically do not translate perceived terrain into platform-specific reachability, while continuous image exchange imposes a high communication cost. We propose an edge-centric, semantic-aware coverage planning framework that integrates aerial terrain perception,
robot-specific traversability
reasoning, and payload-efficient semantic state sharing. Aerial observations are converted into compact semantic grid maps, enabling reachability-constrained area decomposition and capability-aware coverage paths that assign only regions admitted by each
robot's capability profile. The resulting perception-sharing-planning loop feeds semantic corrections into traversability
reasoning and replanning, forming an application-level mechanism motivated by AI-enabled goal-oriented communication envisioned for AI-native 6G networks. For the high-update case, transmitting semantic corrections reduces the application payload by a factor of approximately $82$ relative to periodic full-map sharing. Across matched
benchmark scenarios, the proposed method achieved $91.5\%$ coverage with no capability-infeasible allocations, compared with $78.8\%$ coverage and a $21.5\%$ capability-infeasible allocation rate for LS-MCPP. Semantic corrections update the shared planning state without requiring repeated transmission of the complete map.
Read the full abstract ▾
Artificial Intelligence
EnterpriseBench: Benchmarking LLM Agents on Enterprise-Level Strategic Reasoning and Decision-Making
Min Yang, Yichen Pan, Jinghua Piao et al. (+3 more)
LLM
agents are increasingly expected to support enterprise workflows, where tasks often involve missing information, uncertainty, feedback, and long-term trade-offs. However, existing enterprise and financial
benchmarks mainly test static capabilities such as information extraction, numerical calculation, domain knowledge, and financial QA, leaving interactive and long-horizon decision-making underexplored. To bridge this gap, we introduce EnterpriseBench, a
benchmark that evaluates LLM
agents across this spectrum, from static question answering to dynamic decision-making. Specifically, EnterpriseBench reorganizes existing enterprise and financial QA
datasets into a unified foundational suite annotated by capability and difficulty, and introduces three professional interactive settings: Consulting, based on management-consulting-style business cases for client problem diagnosis through multi-turn information seeking; the Beer Game, adapted from a classic supply-chain management simulation for inventory control under delayed feedback; and Enterprise Digital Twin, a project-based business simulator for workforce, risk, and project planning. Experiments with nine
agent methods under four backbone models show that current
agents have not yet achieved stable, comprehensive, and cross-task reliability in enterprise scenarios. These results show that EnterpriseBench provides a practical
benchmark for evaluating LLM
agents in realistic enterprise strategic
reasoning and decision-making.
Read the full abstract ▾
All authors Min Yang, Yichen Pan, Jinghua Piao, Dandan Song, Yongshun Gong, Yong Li
Artificial Intelligence · Cross-listed from cs.CL
Evaluating and Benchmarking the System One Model Jev
Tobias Deußer, Lorenz Sparrenberg and Rafet Sifa
Jev is a commercial System One model from TypeSafe AI that does not generate text: given a state and typed questions, it returns a choice from fixed options, a position on a rubric, or the probability that a statement is true, with probabilities the vendor describes as calibrated. Such models target small decisions in information access pipelines, such as routing queries, checking grounding, moderating content, or rating against a rubric. We evaluate Jev (jev-1.13.0) zero-shot on 37
datasets spanning classification, routing, natural
language inference, reading comprehension, commonsense
reasoning, moderation, legal clause analysis and rubric scoring, with one frozen template per
dataset and full evaluation splits: 346,009 requests for under USD 10. For reference, we score Qwen3.8-27B and Gemma-4-E4B on identical requests via their exact next-
token probabilities over the options. Jev reaches 95-99% accuracy on IMDB, SST-2, HellaSwag and ARC and 86.7% on Belebele across 122
languages. It beats Qwen on 27 of 37
datasets, with none of Qwen's nine leads outside the bootstrap intervals, and Gemma on all 37. All three models degrade on low-resource
languages, fine-grained or noisy labels, and rubric-based quality judgments. Jev's choice probabilities are well calibrated and support selective prediction. Binary probabilities rank well but are poorly placed relative to a fixed 0.5 threshold; thresholds tuned on training data raise micro-F1 on UNFAIR-ToS from 0.50 to 0.75. Jev answers MMLU's calculation-heavy questions more accurately than other MMLU questions (94% vs. 91%), whereas both open models, and all three on C-Eval, find them harder. Rotating the options leaves Jev's accuracy unchanged and withholding the question drops it to near chance, ruling out shallow memorization but not memorized question-answer pairs. We release the code, harness and all raw responses.
Read the full abstract ▾
Artificial Intelligence
Beyond a single latent space: a dual-latent world model for long-horizon planning
Delin Zhao, Zhengrong Yue, Shaobin Zhuang et al. (+6 more)
Latent world models often struggle with long-horizon planning despite accurate short-term predictions. Recursive rollouts accumulate errors, while distance concentration in high-dimensional latent spaces can weaken goal discrimination. We introduce the Dual-Latent World Model (Dual-WM), which separates local execution and long-range planning through distinct state representations and dynamics models. The low-level model predicts action-conditioned transitions, while the high-level model uses learned macro-actions to plan over longer temporal spans. We also propose Long-Horizon Representation Learning with Weighted Rollout (LoRe), which supervises self-generated predictions at both levels. An analysis of recursive error propagation motivates exponential horizon weights with separate decay rates for the two temporal scales. During planning, the high-level model generates latent subgoals that the low-level model refines into actions for precise execution. We evaluate from-scratch Dual-WM on five goal-conditioned visual control tasks against the task-wise strongest baselines without actor-guided proposals. At goal offsets of 50 and 100 environment steps, mean success increases from 75.9% to 84.4% and from 61.4% to 69.5%, respectively. At offset 100, Dual-WM outperforms these baselines on all five tasks and improves mean success over LeWM by 30.8 percentage points. Ablations and supporting analyses provide evidence of more informative representations for goal evaluation and greater consistency under recursive prediction. These results highlight the value of separating temporal roles and training across multiple horizons for reliable latent planning. Our core implementation is available at https://github.com/DeLin1001/Dual-WM-Official.
Read the full abstract ▾
All authors Delin Zhao, Zhengrong Yue, Shaobin Zhuang, Junlin He, Xiaoyu Chen, Zikang Wang, Yuxin Liu, Limin Wang, Yali Wang
Artificial Intelligence
Flattening the Connectome Spectrum: A Spectral Filter for FC Induces a Pretraining Target for fMRI Encoders
Giovanni Marraffini, Victoria Shevchenko, Carlo Alberto Barbano et al. (+1 more)
Self-supervised pretraining reshaped prediction in
language and
vision, and
brain foundation models (BFMs) inherited its promise. Representations learned from large unlabelled corpora should capture individual functional dynamics and generalise across cohorts. However, kernel ridge regression (KRR) fitted on functional connectivity (FC)
matrices still predicts individual phenotypes more accurately than any BFM we tested. In this paper, we show that KRR is weighted by the
eigenvalues of the FC which are miscalibrated for phenotype prediction. We apply an efficient spectral filter to recalibrate the
eigenvalues of each subject's FC
matrix, enabling the model to exploit more inter-individual variance. Across the 5
datasets, 11 parcellations and 6 prediction targets we tested, we match or exceed the KRR baseline. Based on this finding, we then pretrain a small encoder model on about 4,000 hours of fMRI from 162 open
datasets, whereby we align the pairwise similarities between the
embeddings of recording snippets with those between the recalibrated connectomes. Our model performs on par with the best of the 6 published BFMs we tested while having an order of magnitude fewer parameters. Our encoder performs better than FC on short scans and in smaller cohorts, especially in fingerprinting. We release the pretrained model weights, the code and the pretraining data, preprocessed and parcellated.
Read the full abstract ▾
All authors Giovanni Marraffini, Victoria Shevchenko, Carlo Alberto Barbano, Demian Wassermann