Hardware Architecture
Scalable AXI4 Transaction Monitoring for Mixed-Criticality SoCs: From Phase-Level Precision to ID-Level Efficiency
Chaoqun Liang, Thomas Benz, Alessandro Ottaviano et al. (+4 more)
Mixed-criticality Systems-on-Chip (SoCs) with on-chip interconnects based on the AXI4 open standard protocol lack a protocol-level timeout mechanism, exposing systems to deadlocks and missed real-time deadlines when subordinate devices or managers fail or stall due to hardware faults, radiation-induced upsets, or software errors. This work presents a configurable hardware intellectual property (IP), non-intrusive in fault-free operation, that detects AXI4 protocol violations and timing faults at runtime and restores interconnect liveness through a cut-and- drain isolation mechanism. To address the fundamental trade-off between monitoring granularity and area cost, we introduce three designs at decreasing monitoring granularity: Phase-Level Track-ing (PLT), which provides cycle-accurate fault localization across individual protocol phases; Channel-Level Tracking (CLT), which coalesces per-phase monitors into channel-level supervision; and ID-Level Tracking (ILT), which achieves sub-linear area scaling by monitoring only per-ID transaction boundaries. Synthesized in GlobalFoundries 12 nm technology, CLT reduces area by 36.7% relative to PLT while preserving worst-case detection bounds at a minimal detection latency overhead, whereas ILT achieves an 89.2% area reduction suitable for tightly constrained deployments at the cost of a 3.7x higher median detection latency with coarser fault localization. Fault injection campaigns on a RISC-V SoC across 1.2 million scenarios confirm that no fault manifesting as an AXI4 protocol or liveness violation escaped detection, with observed detection latencies consistently bounded by theoretical worst-case predictions.
Read the full abstract ▾
All authors Chaoqun Liang, Thomas Benz, Alessandro Ottaviano, Michael Rogenmoser, Luca Benini, Angelo Garofalo, Davide Rossi
Robotics
A Hybrid PEM-GP Framework for Uncertainty-Aware System Identification of Quadcopters
Abdallah Ghoul, Ismail Khalil Bousserhane and Kadri Boufeldja
Accurate dynamic models play a central role in achieving reliable control of quadcopters. Classical system identification methods remain widely used, mainly because of their interpretability. However, they often fail to capture important nonlinear effects, especially in small-scale aerial platforms where such effects become more pronounced. Data-driven approaches offer a different perspective. They can represent complex nonlinear dynamics more effectively, but this comes at the cost of reduced interpretability and the absence of well-calibrated uncertainty estimates. In this work, we propose a framework that combines physics-based modeling with data-driven learning, while explicitly accounting for uncertainty. A physics-based model is first identified using the Prediction Error Method (PEM), which captures the main structure of the system. The remaining dynamics are then modeled using a Gaussian Process (GP), allowing the residual behavior to be learned directly from data. This separation makes it possible to distinguish between known physical effects and unmodeled dynamics. The proposed framework is validated on a Duckiedrone-like experimental setup. The results show that the PEM-GP model achieves prediction accuracy comparable to that of a Long Short-Term
Memory (LSTM) network, while additionally providing calibrated uncertainty estimates. This combination improves model reliability and supports uncertainty-aware decision-making.
Read the full abstract ▾
Systems and Control
Generalization as a robust performance property of learning-enabled dynamical systems
Filippo Fabiani
By focusing on algorithmic stability as a means of establishing out-of-sample bounds, we provide a system-theoretic interpretation of generalization in learning-enabled dynamical systems arising in data-driven optimization and feedback control approximation. Given two neighboring
datasets, we specifically model sample replacement as an exogenous disturbance acting on a sensitivity system, while the incremental behavior of the data-dependent operator is encoded through an integral quadratic constraint. By relying on dissipativity arguments, we establish a
matrix inequality-based certificate and a uniform stability bound that separates the one-sample sensitivity of the learned operator, and an
algorithm-dependent dynamical gain. The latter can then be optimized, offering a tractable tool for certifying and comparing generalization capabilities of learning dynamics. We show that our results recover classical ones for gradient descent, apply naturally to momentum-based methods such as heavy-ball and Nesterov acceleration, and extend to data-driven control.
Read the full abstract ▾
Artificial Intelligence
EvoSkill Injection: Red-Teaming Autonomous Skill Generation and Evolution in Self-Evolving Agents
Doyun Kim, Chanwoo Kim, Sugyeong Eo et al. (+2 more)
LLM-based
agent systems increasingly adopt skill-based architectures to reduce repetitive
reasoning costs and improve stable, efficient task execution. Recent studies propose self-evolving
agents that autonomously generate, refine, and reuse skills from past experiences to enable continuous capability
evolution. However, autonomous skill
evolution introduces a new attack surface in which malicious capabilities are generated, stored, and reused as legitimate skills. In this paper, we define EvoSkill Injection as a threat model targeting the autonomous skill generation and
evolution pipeline of self-evolving
agents. We further propose SARGE (Red-teaming Autonomous Skill Generation and
Evolution in self-evolving
agents), a red-teaming framework for evaluating this threat model through iterative generation, escalation, and reinforcement interactions. To support our framework, we construct EvoSkillBench, a
benchmark dataset of malicious interaction trajectories for inducing malicious skill formation in self-evolving
agents, and introduce EvoSkillSafetyBench, a post-attack
benchmark for evaluating whether injected malicious skills are subsequently retrieved and activated as harmful behaviors. Our evaluation shows that SARGE induces malicious skill formation and that injected skills are persistently stored and repeatedly activated, highlighting the risk of persistent capability corruption.
Read the full abstract ▾
All authors Doyun Kim, Chanwoo Kim, Sugyeong Eo, Yeo-Chan Yoon, Chanjun Park
Computation and Language
Lies We Can See: Joint Verbal and Non-Verbal Deception by VLM Agents in Embodied Social Interactions
Jaewoo Ahn, Junseo Kim, Hyunseo Kim et al. (+4 more)
Strategic deception by LLM and VLM
agents has emerged as a central AI
alignment and safety concern. Social-deduction games (where each player holds a hidden role and communicates with others to deduce identities) serve as the canonical testbed, particularly in multi-
agent settings. Existing testbeds, however, are text-only and run on a single fixed
agent configuration, missing the non-verbal sensorimotor channels treated as core by deception taxonomies and leaving it ambiguous whether an observed behavior reflects the underlying model or the surrounding harness. We introduce MineAmongUs, a 3D
multimodal Among Us sandbox where imposter
agents must deceive crewmates through joint verbal and non-verbal action. We also propose ARIA, a configurable VLM-
agent harness that exposes five cognitive-component ablation axes; and an atom- and arc-level annotation scheme grounded in deception taxonomies and operationalized at scale by an LLM-as-a-Judge reaching near-human atom-labeling agreement. Empirical results show that VLM
agents pursue imposter wins through joint verbal and non-verbal deception, with non-verbal channels emerging as the more decisive winning contributors across both harness ablation and cross-VLM evaluation. Taken together, our work opens a new path for
embodied VLM-
agent alignment research.
Read the full abstract ▾
All authors Jaewoo Ahn, Junseo Kim, Hyunseo Kim, Heeseung Yun, Jaehyeon Son, Zsolt Kira, Gunhee Kim
Computation and Language
Ceiling-Clipped Acceptance Histograms Indicate Stranded Speed-up in Block-Diffusion Speculative Decoding
Ephrem Wu
Speculative decoding speeds up generation with an efficient draft model (drafter) that proposes
tokens for a target model to verify in one pass, preserving the target's output distribution. High-acceptance block-
diffusion drafters such as DFlash and DFlare fill an entire block in one parallel pass. In many cycles, the target accepts the whole block, so the drafter exhausts its trained block horizon before verification fails. We call this unrealized acceptance stranded speed-up. A mean committed length, per
prompt or per cycle, hides it, whereas the acceptance histogram exposes it as a spike in the ceiling bin, the fraction of cycles that accept the entire block. We recommend the histogram as a preflight check before spending training compute. Naively widening the block at inference does not recover the speed-up, because once the block outgrows its training size, the drafter's bidirectional
attention shifts its distribution even at early positions and erodes front-of-block verification. Instead, we post-train the drafter on a longer block with a short curriculum that emphasizes the newly exposed positions, a method we call DBloom. Expanding the pretrained DFlash and DFlare drafters from block size 16 to 24 across Qwen3-8B and Qwen3-4B targets raises the per-
prompt committed length on the high-ceiling
benchmarks by a median of +0.8
tokens (up to +1.1). Once continuation fine-tuning precedes expansion, the increase reaches 1.37
tokens. The same expansion also lifts committed length on all seven
benchmarks for Gemma-4-12B-IT, a different model family, by a median of +0.41
tokens (Arm A), and the full continuation-then-expand pipeline (Arm B) adds +0.29 to +0.98
tokens over the same B16 drafter. In a
prompt-matched comparison against JetSpec, a contemporary tree-based drafter not used in our design, DBloom commits more
tokens on every
benchmark at tree budgets up to 64 nodes.
Read the full abstract ▾
Computation and Language
Learning to Reason and Use Tools through Unsupervised Fine-Tuning in Task-Oriented Dialog Systems
Markel Ferro and Oier Lopez de Lacalle
Current dialogue systems struggle with dynamic information
retrieval, often leading to
hallucinations and lower response accuracy. We address this by adapting the ReAct framework for Task-Oriented Dialogue, enabling Large
Language Models (LLMs) to access external knowledge and produce factual responses. Mainly, we propose an unsupervised fine-tuning pipeline that harvests
reasoning trajectories via in-context learning inference. High-quality samples are filtered using an LLM-based judge to construct a robust training set. This is enhanced by a unsupervised self-improvement loop, where improved checkpoints generate increasingly better trajectories for subsequent fine-tuning iterations. Experiments on the SIMMC
dataset demonstrate that ReAct-based systems outperform baselines due to superior
reasoning and tool use. Notably, our fine-tuned 8B model surpasses a 70B in-context system. Finally, we present an error analysis, impact of scene complexity, and cross-domain generalization.
Read the full abstract ▾
Computation and Language
Generative Models Enhanced by Sequence Labelling and Aspect-Code Switching Improve Cross-lingual Aspect-Based Sentiment Analysis
Jakub Šmíd, Pavel Přibáň and Pavel Král
Cross-lingual aspect-based sentiment analysis (ABSA) transfers knowledge from a source
language with annotated data to a target
language, enabling fine-grained sentiment analysis without annotated target-
language data. While monolingual ABSA has seen significant progress, cross-lingual ABSA remains underexplored, especially for complex tasks involving multiple sentiment elements like target-aspect-sentiment detection (TASD). In this paper, we propose a novel SeqLab framework that enhances cross-lingual ABSA using a sequence-to-sequence model with an auxiliary sequence-labelling task performed by the encoder, enhancing aspect term recognition and sentiment predictions. Additionally, we incorporate aspect-code switching (ACS), a translation-based technique that swaps aspect terms between source and translated sentences, generating additional training data to enhance the model's cross-lingual understanding. We evaluate our approach across eleven
languages, three domains, and two backbone models, surpassing previous state-of-the-art results for the commonly studied E2E-ABSA task. Unlike most prior work that relies solely on English as the source
language, we systematically assess different source-target
language pairs and extend our evaluation to the more challenging, yet underexplored TASD task in cross-lingual settings. Finally, we provide a detailed error analysis highlighting key challenges and limitations.
Read the full abstract ▾
Human-Computer Interaction
Towards Cognitive Process-Aware Proactive Writing Support
Masahiro Yoshida, Atsuya Kobayashi, Kei Tateno et al. (+1 more)
Large
language models can support writing, but existing tools require users to explicitly articulate
prompts-particularly burdensome in creative writing, where intentions are often ambiguous. Proactive support that infers users' needs from writing interactions could alleviate this burden, but raises two challenges: determining what support to provide and when to intervene. This work focuses on the former. We hypothesize that Flower and Hayes' cognitive process theory of writing-which characterizes writing through six cognitive processes-offers an interpretable bridge between observable writing behavior and appropriate support types. Through a formative study and literature review, we identify 14 writing support types associated with these cognitive processes, along with characteristic interaction behaviors linked to each process. We then instantiate this framework in AToM CoWriter, which infers support needs from writing interactions and document context. Two within-subjects studies (N = 21) provide initial evidence that this approach improves expressiveness and idea exploration, and that cognitive process inference increases engagement with proactive suggestions. These findings suggest that cognitive processes can provide a promising basis for support selection in proactive writing systems.
Read the full abstract ▾
All authors Masahiro Yoshida, Atsuya Kobayashi, Kei Tateno, Xiang 'Anthony' Chen
Computer Vision
ObjectSplat: Improving Mesh Fidelity and Interactivity for 3D Scenes via Object-Level Mesh Splatting
Minhas Kamal, Hiranya Garbha Kumar, Mahedi Kamal et al. (+1 more)
Splatting-based
algorithms reconstruct photorealistic, real-time-renderable, and mesh-exportable 3D scenes from regular images, but they represent a scene as a single monolithic field. Therefore, the reconstruction has no object-level structure, leaving it infeasible for downstream editing or interaction. Moreover, regions that are never directly observed in the input scans are contaminated by the surrounding texture and left uncorrected, capping both mesh fidelity and novel-view synthesis. We propose a decompose-before-reconstruct approach: we segment the instances out of every frame, consider the remaining as background and inpaint it, reconstruct each instance and the background independently with mesh splatting, and compose them into a single scene. Our method significantly improves mesh fidelity (over a 5% gain in F-score) and novel-view synthesis, while supporting object-wise modifiability and interactivity. The code will be made publicly available.
Read the full abstract ▾
All authors Minhas Kamal, Hiranya Garbha Kumar, Mahedi Kamal, Balakrishnan Prabhakaran
Computer Vision
Whole-Slide Image Analysis under Realistic Few-Shot Annotation Protocols
Tiffanie Godelaine, Maxime Zanella, Karim El Khoury et al. (+2 more)
Automating the analysis of whole-slide images has high clinical value, since characterizing cancers requires examining them in detail. Such analysis increasingly relies on
vision-
language models that provide patch-level zero-shot predictions. However, these predictions remain noisy and must be refined with a few annotations. A promising paradigm for this refinement is few-shot transduction. Rather than treating each patch independently, these methods leverage the relations between patches, together with a few annotations, to refine all predictions jointly. However, current transductive methods are evaluated under conditions that overlook key properties of whole-slide images: (i)
datasets consist of independent patches extracted from multiple slides, ignoring the complex tissue organization; (ii)
datasets are mostly balanced, whereas a single whole-slide image exhibits severe class imbalance, with several classes absent; and (iii) annotations are sampled at random, without reflecting how a pathologist annotates a limited number of regions. To align the transduction paradigm to realistic whole-slide settings, we introduce the following contributions. First, we propose SlideCRF, which adapts conditional random fields for whole-slide images by combining spatial and biological cues while accounting for classes that may be absent from a given slide. Second, we provide a set of realistic annotation protocols, based on spatially localized clicks and scribbles, modeling different pathologist interactions, such as the iterative correction of model errors. Across four
datasets, we show that SlideCRF outperforms current transductive methods in macro F1, improving over the zero-shot predictions by +24.2% and +37.5% with one and 16 clicks per present class, respectively.
Read the full abstract ▾
All authors Tiffanie Godelaine, Maxime Zanella, Karim El Khoury, Benoit Macq, Christophe De Vleeschouwer
Artificial Intelligence
From Metaheuristics to Exact Methods: A CP-SAT Approach for Multi-Objective Healthcare Workforce Scheduling
Vipul Patel, Anirudh Deodhar and Dagnachew Birru
Healthcare workforce scheduling is an NP-hard optimization problem requiring simultaneous satisfaction of labor regulations, coverage requirements, employee preferences and cost objectives. Existing approaches (genetic
algorithms, integer programming, constraint programming) model 6-12 constraints at shift-level granularity and cannot guarantee regulatory compliance. They also lack support for multi-role, multi-skill heterogeneity, mandatory break scheduling with midpoint control, acuity-weighted workload equity, sub-shift granularity, inter-week stability, and cross-midnight shifts. This paper presents CP-SAT: a Constraint Programming formulation for multi-role, multi-skill healthcare scheduling. CP-SAT enforces 14 hard constraints guaranteeing zero regulatory violations, while optimizing 15 soft objectives via a unified weighted penalty function. Contributions include a shift-window decomposition enabling break scheduling with centrality control, acuity-weighted workload equity, multi-granularity resolution from 15 minutes to 1 day, inter-week stability, and grid-offset preprocessing mapping cross-midnight shifts into a single scheduling day without solver changes. CP-SAT is evaluated on 18 instances: five synthetic hospital units (10-33 nurses), 10 INRC-II
benchmarks (5-80 nurses, up to 8-week horizons) and 3 NRP-23 compatible instances (10-25 nurses) with cross-midnight Night shifts. Results: zero hard-constraint violations across all 18 instances by construction; proven optimality on INRC-II n005w4 (objective 118, gap 0.0%, 104s); feasible schedules scaling to 179,800 variables and 351,425 constraints (80 nurses); service quality improved 50-67% over MOGA; and model size scaling near-linearly at approximately 4,400 variables per employee. The formulation enforces 29 total constraints (14 hard, 15 soft), nearly three times the industry average.
Read the full abstract ▾
Machine Learning · Cross-listed from eess.SP
Benchmarking External Generalization of SPD Matrix Learning for Resting-State fMRI Connectome Prediction
Ce Ju, Antoine Collas, Florent Bouchard et al. (+1 more)
Resting-state functional
magnetic resonance imaging (rs-fMRI) functional connectivity (FC)
matrices are widely used for individual-level prediction, but strong performance within one cohort may not generalize to a new cohort. We ask whether within-
dataset performance remains when the test data come from an entirely held-out rs-fMRI
dataset. Each scan is represented as a regularized symmetric positive definite (SPD) correlation connectome, which allows methods to use the geometry of the SPD
manifold. We introduce a reproducible age-prediction
benchmark across six rs-fMRI
datasets: COBRE, ADNIDOD, Cam-CAN, ABIDE, OASIS-3, and ADNI. The
benchmark compares a vectorized correlation baseline, Tangent-Space Ridge, SPDNet, and split-wise Riemannian harmonization under within-
dataset GroupKFold, pooled GroupKFold, and leave-one-
dataset-out (LODO) evaluation. Within-
dataset and pooled GroupKFold results are substantially more favorable than LODO results. When an entire
dataset is held out, prediction error increases, differences among methods narrow, and performance is strongly affected by age-range mismatch and cohort heterogeneity. The
benchmark provides common inputs, model settings, data splits, and analysis scripts so that future SPD
matrix learning methods can be evaluated under the same external-validation protocol.
Read the full abstract ▾
All authors Ce Ju, Antoine Collas, Florent Bouchard, Bertrand Thirion
Machine Learning
Inherent Trade-offs when Enforcing Correct Data Symmetries in Multi-head Self-attention
Tīkun Ông and Georg Bökman
We give a complete characterization of equivariant multi-head self-
attention (MHSA): if an MHSA layer is equivariant to a
symmetry group $G$, then $G$ can only act by permuting head-clusters, with QK and OV
matrices satisfying an equivariance constraint tied to the group action. As a consequence, we prove that any fixed MHSA architecture that achieves exact equivariance by polynomially parameterizing unconstrained MHSA parameters inevitably leads to expressivity loss within the class of equivariant maps: the equivariance locus of unconstrained MHSA forms a union of extremely many Zariski-irreducible components in a reduced parameter space, and any single architecture covers at most one. For $G=D_4$ acting on $C$ copies of the regular representation as the
token feature space, we show that there are $\Omega(C^{64})$ components for eight
attention heads. We illustrate this with experiments on artificial tasks and show that the predicted head-cluster structures can arise naturally when the
attention layer is pressured to become equivariant.
Read the full abstract ▾
Artificial Intelligence
DERELAB: Probing Defeasible Reasoning and Confirmation Bias in LLMs with a Generative Benchmark
Jayanta Sadhu, Sayem Shahad and Kenneth Marino
Defeasible
reasoning is a type of
reasoning where inferences are drawn from plausible current evidence, but can be retracted upon the introduction of newer evidence. Although recent studies have examined
language-model behaviors in defeasible
reasoning, the
datasets have been static and lack wide coverage of non-monotonic
reasoning categories. We introduce DeReLab, a generative framework that produces multi-turn belief-updating conversations from parameterized graph structures across default and inheritance
reasoning, with formally verified ground truth at every turn, enabling controlled measurement of how models respond to confirming and disconfirming evidence. This controlled generation process creates a testbed for experimental designs that isolate specific
reasoning demands. Applying this capability to the study of confirmation bias, we evaluate nine open and proprietary large
language models and find that nearly all exhibit a systematic tendency to accept congruent evidence while resisting incongruent updates, with several models correctly identifying a weakening update yet failing to revise their conclusion. We believe our work and findings will facilitate future research on evaluating
language models in defeasible
reasoning.
Read the full abstract ▾
Computer Vision
SePArate: Segmenting Patterns from Defects in Wafer Manufacturing Using Weak Supervision
Dain Kwon, Changmin Shin, Sunjong Park et al. (+5 more)
In
semiconductor manufacturing, defect analysis is essential, but manual inspection cannot scale. However, existing automated inspection methods remain insufficient for root-cause analysis and process optimization. To this end, we present SePArate, a weakly supervised wafer defect
segmentation method. SePArate enables pixel-level separation of patterns by leveraging only image-level annotations. It consists of a three-phase training: encoder pretraining, knowledge transfer to learn spatial cues, and training on synthetic mixed-defect data for accurate
segmentation. Experiments demonstrate that SePArate outperforms the baselines.
Read the full abstract ▾
All authors Dain Kwon, Changmin Shin, Sunjong Park, Kanghyun Choi, Hyeyoon Lee, Jaewon Jang, Minseok Choi, Jinho Lee
Information Theory · Cross-listed from math.CO
Edge codes constructed from unicyclic graphs
Sara Asensio, Giulia Gaggero, Naveena Ragunathan et al. (+2 more)
Jaramillo-Velez recently introduced edge codes, a new class of toric evaluation codes constructed from the edges of a (hyper)graph $\mathcal{H}$. In the case that $\mathcal{H}$ is a tree, Jaramillo-Velez computed both the minimum distance and the weight distribution of the associated code. In this paper, we study edge codes associated to unicyclic graphs. Our most striking result is that computing the parameters of these codes is subtle in the case that the induced cycle has an even length because these values will depend on certain conditions regarding the length of the cycle and the size of the base field.
Read the full abstract ▾
All authors Sara Asensio, Giulia Gaggero, Naveena Ragunathan, Abhilash Saha, Adam Van Tuyl
Machine Learning
Locally-Guided Actor-Critic: Training a Goal-conditioned Actor with a Subgoal-aware Critic
Olivier Serris, Stéphane Doncieux and Olivier Sigaud
Goal-conditioned reinforcement learning struggles with long horizons when rewards are sparse. While a planner can provide subgoals to guide a low-level policy, its use at test time may introduce practical subgoal management difficulties. An alternative paradigm utilizes a high-level planner to assist learning, while the policy remains conditioned only on the final goal, enabling planner-free deployment. Among these methods, Reinforcement Learning with Imagined Subgoals (RIS) introduces a regularization term that encourages the policy to take the same actions for the final goal as it does for an intermediate goal. This regularization, however, may lead to goal-chaining issues when intermediate goals are low-dimensional. Potential-based reward shaping (PBRS) translates plans into an additional reward while ensuring that the optimal policy remains unchanged. Yet, it can generate deceptive rewards in terminal states. We study these failure cases and first propose an alternative reward shaping method (RS) that removes these deceptive rewards at the expense of theoretical guarantees of PBRS. Similar to this RS variant, we then propose another method named Locally-Guided Actor Critic (LG-AC) that rewards the
agent for reaching intermediate goals. Unlike RS, where intermediate rewards are implicit in the shaping signal, we explicitly condition a value
estimator on the full sequence of intermediate goals but represent the value function as a sum of subgoal-conditioned value functions, enabling dense hindsight relabeling. We evaluate all these methods in tasks with challenging goal-chaining requirements and empirically highlight specific cases in which either action regularization or reward shaping yield low performance, while LG-AC achieves the best overall performance across tasks.
Read the full abstract ▾
Artificial Intelligence
Dense Clinical Contrasts Enhance Medical Knowledge Updating in Large Language Models
Yangmin Huang, Shu Quan, He Geng et al. (+5 more)
Medical knowledge changes continually, making large
language models vulnerable to relying on outdated yet clinically plausible information. We study whether the format of supervision affects medical knowledge updating under a matched training-budget setting. We introduce SEER-Bench, a temporally anchored oncology-staging
benchmark curated from the latest versioned SEER Research Data release, and render identical medical update events from NCCN oncology guidelines into four supervision formats: EMQ, MSQ, FITB, and SAQ. Across SEER-Bench and HealthBench Professional, EMQ gives the most stable external transfer and retention among same-budget SFT variants. With EMQ supervision, the updated 4B model produces competitive results on temporally anchored oncology staging, reaching 64.8% answer accuracy and 59.6% rationale accuracy on SEER-Bench. Diagnostic analyses suggest that EMQ exposes denser clinical contrast signals while preserving discriminative representations with smaller movement from the base model. These results show that medical knowledge updating depends not only on the update
algorithm, but also on how knowledge is structured as supervision.
Read the full abstract ▾
All authors Yangmin Huang, Shu Quan, He Geng, Xin Ye, Qianyun Du, Zhiyang He, Jiaxue Hu, Xiaodong Tao
Computer Vision
ImageCAS-X: a dataset and benchmark for coronary artery segmentation and centerline extraction in coronary CT angiography
Kit M. Bransby, Esther Øksnebjerg, Kristoffer Kjær et al. (+7 more)
Accurate
segmentation of the coronary vessel lumen is a prerequisite for quantitative assessment of atherosclerotic plaque and perivascular adipose tissue in coronary computed
tomography angiography (CCTA). Cardiologists rely on semi-automated methods for this task because manual vessel tracing and
segmentation are labour-intensive. Although many automated methods have been proposed, their validation remains limited by the lack of large, high-quality publicly available
datasets. We provide a new
dataset of voxel-wise annotations of the vessel lumen and coronary segments, alongside centerlines, and mesh surfaces for 800 scans from the publicly available ImageCAS
dataset. Using this
dataset, we
benchmark established lumen
segmentation methods against inter-observer variability, stratifying performance by disease, image quality, coronary dominance, coronary segment, vessel diameter, and lumen attenuation. These labels allow
segmentation accuracy to be described in anatomical and clinical context rather than reported as a single aggregate score. The
dataset supports the development and validation of methods for lumen
segmentation, plaque and perivascular quantification, and haemodynamic modelling.
Read the full abstract ▾
All authors Kit M. Bransby, Esther Øksnebjerg, Kristoffer Kjær, Jacob Kirkeby, Yasmin El Youssef, Aïda Jiménez, Philip R. Pedersson, Martina C. de Knegt, Klaus F. Kofoed, Rasmus R. Paulsen
Cryptography and Security
Why Are LLM Backdoor Defenses Fragmented? A Feature-Level Explanation with Sparse Autoencoders
Yizhe Zeng, Chenxu Niu, Wei Zhang et al. (+7 more)
Backdoor attacks pose a serious threat to large
language models (LLMs), but existing defenses remain fragmented, failing to pro?vide unified defense against both dirty-label and clean-label attacks. To investigate why such fragmentation arises, we present the first systematic feature-level mechanistic analysis of LLM
backdoors using sparse autoencoders (SAEs). Starting from a 2 x 2 comparison of clean and poisoned models on clean and triggered inputs, we trace
backdoor-induced logit shifts to high-contributing SAE features and categorize them into four roles: interac?tion, suppressed, mixed, and weight-modified features. This taxonomy reveals system?atic encoding differences: dirty-label back?doors are dominated by isolated interaction features, whereas clean-label
backdoors rely more on heterogeneous mixtures of mixed and weight-modified features. These differ?ences explain why existing defenses remain fragmented across attack paradigms. We val?idate this hypothesis through inference-time feature clamping, which reduces ASR to at most 10.8% in most dirty-label settings and at most 15.4% in the majority of clean-label settings, while preserving benign-task perfor?mance. These results show that SAE-based analysis can explain defense fragmentation and guide interpretable
backdoor mitigation.
Read the full abstract ▾
All authors Yizhe Zeng, Chenxu Niu, Wei Zhang, Hao Huang, Yunpeng Li, Dongxu Han, Dan Du, Cheng Hong, Hequn Xian, Yuling Liu
Computer Vision
Real-Time Scene-Adaptive Tone Mapping for High-Dynamic Range Object Detection
Gongzhe Li, Linwei Qiu, Peibei Cao et al. (+3 more)
High-dynamic-range (HDR) images, with their rich tone and detail reproduction, hold significant potential to enhance computer
vision systems, particularly in autonomous driving. However, most neural networks for embedded systems are trained on low-dynamic-range (LDR) inputs and suffer substantial performance degradation when handling high-bit-depth HDR images due to the challenges posed by extreme dynamic ranges. In this paper, we propose a novel tone mapping method that not only bridges the gap between HDR RAW inputs and the LDR sRGB requirements of detection networks but also achieves end-to-end optimization with downstream tasks. Instead of relying on the traditional image signal processing (ISP) pipeline, we introduce neural photometric calibration to regularize dynamic ranges and a scaling-invariant local tone mapping model to preserve image details. In addition, our architecture also supports performance transfer finetuning, enabling efficient adaptation from the LDR sRGB images to the HDR RAW images with minimal cost. The proposed method outperforms traditional tone mapping
algorithms and advanced AI-ISP methods in challenging automotive HDR scenes. Moreover, our pipeline achieves real-time processing of 4K high-bit-depth HDR inputs on NVIDIA Jetson platforms.
Read the full abstract ▾
All authors Gongzhe Li, Linwei Qiu, Peibei Cao, Fengying Xie, Xiangyang Ji, Qilin Sun
Computation and Language
SemPOI-RL: Aligning LLM Semantic Reasoning for Interpretable Out-of-Town POI Sequential Generation
Yunqi Liu, Yang Zhang, Ruixing Zhang et al. (+4 more)
Large
language models (LLMs) exhibit strong semantic
reasoning and open-ended generation abilities, but aligning these abilities with structured sequential generation remains challenging. This challenge is particularly evident in out-of-town (OOT) POI sequence generation, where a model must infer transferable travel intent from a user's hometown behaviors, adapt to cross-city interest drift, and generate a coherent destination trajectory under structural constraints. Existing approaches either rely on latent ID-based transfer with limited interpretability or directly use LLMs for sequence generation without explicitly grounding inferred semantics into position-aware predictions. To address this gap, we propose SemPOI-RL, a framework that aligns LLM semantic
reasoning with structured sequence generation for interpretable OOT recommendation. Specifically, we first fine-tune an LLM to infer destination-oriented travel styles from users' hometown trajectories, using natural
language as an interpretable semantic intermediate. We then introduce a Semantic POI
Alignment Module (SPAM) to ground these inferred styles into a style-conditioned masked autoencoder for position-aware trajectory generation. Finally, we apply reinforcement learning with recommendation-oriented rewards to align LLM-generated styles with downstream sequence quality. Experiments on two real-world
datasets show that SemPOI-RL consistently outperforms both traditional recommenders and direct LLM baselines, while providing interpretable style attribution across different phases of a trip. The code is available at https://github.com/Wind-Flipped/SemPOI-RL .
Read the full abstract ▾
All authors Yunqi Liu, Yang Zhang, Ruixing Zhang, Liangzhe Han, Yi Qiao, Tongyu Zhu, Leilei Sun
Computation and Language
Beyond Polarization: The Generative Constraint of Chain-of-Thought in Pointwise Reranking
Xiaoyang Chen, Jie Liu, Haijin Liang et al. (+5 more)
In pointwise document reranking, Chain-of-Thought models typically underperform direct scoring models. While existing diagnostics attribute this to inferior classification, score polarization, or calibration breakdown, whether targeted training can bridge this gap remains unclear. Our empirical study first confirms that this gap is stable across scales up to 32B parameters, ruling out model and data capacity confounders. We then apply stress tests utilizing reinforcement learning, fine-grained supervision, and architectural decoupling to explicitly repair these deviations. Although these interventions improve classification accuracy and absolute scores, the relative ranking gap persists. These findings suggest that, within the pointwise scoring paradigm, routing continuous relevance semantics through discrete text constrains ranking signal resolution, revealing a bottleneck that is stable and difficult to overcome under current standard methods, rather than an easily resolvable training bias.
Read the full abstract ▾
All authors Xiaoyang Chen, Jie Liu, Haijin Liang, Haibo Shi, Jin Ma, Ben He, Yingfei Sun, Dezhi Ye
Computation and Language
Co-Evolving Actor-Conditioned Critics for Non-Verifiable Generation
Jinyoung Kim, Muhammad Khalifa, Lajanugen Logeswaran et al. (+4 more)
Natural-
language critiques provide supervision beyond scalar rewards for non-verifiable generation, which lacks deterministic verifiers. In critique-guided refinement, a critic gives feedback on an initial response and an actor revises it. However, final revision quality does not reveal whether the critique was actually useful: a capable actor may improve without following the feedback, while valid feedback may fail if the actor cannot execute it. We frame critique as actor-conditioned revision guidance, where usefulness depends on whether the feedback helps the target actor address the intended weakness. We introduce TAIScore (Targeted Actionable Improvement Score), a reward that evaluates the instruction, initial response, critique, and revision together, assessing whether the critique targets a real weakness, whether the actor follows it, and whether the intended aspect improves. We use this reward to train an actor-tailored critic with GRPO, and use critique-guided refinements to construct DPO preference pairs for the actor, forming a co-evolving critic-actor loop where the critic adapts to the actor's changing capability. Experiments show that an 8B critic trained with TAIScore outperforms both a zero-shot 120B critic and critics trained with outcome-only or critique-only reward signals. Co-evolving the critic and actor further improves performance, suggesting that effective critique supervision should adapt as the actor changes.
Read the full abstract ▾
All authors Jinyoung Kim, Muhammad Khalifa, Lajanugen Logeswaran, Jaekyeom Kim, Moontae Lee, Honglak Lee, Lu Wang
Artificial Intelligence
Scaffolding Foundation Models into Physical-World Agents Pushes the Frontier of Long-Horizon Navigation
Zixing Lei, Gengze Zhou, Xiong-Hui Chen et al. (+7 more)
Long-horizon physical-world
agents must reason over distant goals while grounding decisions in reliable closed-loop behavior. Today's foundation models split these capabilities:
vision-
language models (VLMs) infer missing information and adapt high-level plans but remain brittle and inefficient at repeated
navigation grounding, while
navigation foundation models (NFMs) robustly execute semantic goals but operate as bounded episodes without persistent task-level
reasoning. We introduce NavMCP, an agentic scaffolding framework that couples a VLM
reasoning agent with an NFM executor for long-horizon exploration. The VLM decides what evidence to seek, where to search, and when to stop, while the NFM grounds each semantic sub-goal into closed-loop
navigation. Three channels structure their collaboration: intent translates evidence needs into
navigation calls, observation converts rollouts into source-grounded trajectory evidence, and
memory accumulates findings, negative evidence, and unresolved goals across calls. This design turns isolated
navigation rollouts into persistent
embodied interaction without retraining either model. On
Embodied Question Answering, NavMCP achieves state-of-the-art results on HM-EQA, MT-HM3D, and EXPRESS-Bench. Under matched
agent and executor backbones, it outperforms an episodic interface by 14.9 percentage points on HM-EQA. On a Unitree Go2, NavMCP reaches 78.3% success, with its margin over the strongest baseline growing from 10 to 45 points as the task horizon increases. These results demonstrate the potential of scaffolding complementary foundation models into long-horizon physical-world
agents.
Read the full abstract ▾
All authors Zixing Lei, Gengze Zhou, Xiong-Hui Chen, Jiazhao Zhang, Yiyang Huang, Hang Yin, Haoqi Yuan, Qi Wu, Weixin Li, Siheng Chen
Computation and Language
When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Models
Jiaqi Wei, Xiang Zhang, Yuejin Yang et al. (+10 more)
As pretraining scaling laws approach saturation, Test-Time Scaling (TTS) has emerged as an important direction for improving
reasoning by allocating inference-time compute to a fixed model prior. Viewed at a high level, TTS reframes inference as search over a space of partial
reasoning states. While Chain-of-Thought (CoT) exposes intermediate steps, common instantiations rely on single-trajectory decoding, limiting recovery from early errors and exploration. This survey systematizes recent progress in tree-search-based
reasoning, viewing inference as instance-specific optimization rather than decoding. We trace the
evolution from uninformed search to Monte Carlo Tree Search (MCTS), highlighting how sampling-based control supports principled exploration-exploitation trade-offs. To unify a fragmented literature, we introduce a Unified Design Space spanning search
topology, evaluation signals, and control dynamics, and advocate a standardized compute-reporting abstraction to make compute-accuracy trade-offs explicit and comparable.
Read the full abstract ▾
All authors Jiaqi Wei, Xiang Zhang, Yuejin Yang, Wenxuan Huang, Juntai Cao, Sheng Xu, Xiang Zhuang, Zhangyang Gao, Muhammad Abdul-Mageed, Laks VS Lakshmanan, Chenyu You, Wanli Ouyang, Siqi Sun
Machine Learning
TopGQ: Fast GNN Post-Training Quantization Leveraging Topology Information
Dain Kwon, Kanghyun Choi, Hyeyoon Lee et al. (+4 more)
Existing GNN quantization methods suffer from considerable quantization overhead, which severely limits their practical usage in real-world scenarios. To this end, we present TopGQ, an accurate post-training GNN quantization framework, alleviating redundant quantization overhead. We propose dual-axis scale absorption, which enables activation quantization along both the outer and inner dimensions by merging one into the adjacency
matrix. On top of that, we introduce TopPIN, a proxy for nodes' local structure, and use it to group nodes with similar
topology during quantization. Experimental results show that TopGQ reduces quantization time by an order of magnitude while preserving accuracy.
Read the full abstract ▾
All authors Dain Kwon, Kanghyun Choi, Hyeyoon Lee, Sunjong Park, Seoyong Lee, Sukjin Kim, Jinho Lee
Computation and Language
Quantitative Evidence Mining for Plausibility-Aware Biomedical AI: A Narrative Review and Conceptual Framework
Negin Sadat Babaiha, Stefan Geissler, Marie-Christine Simon et al. (+2 more)
Biomedical artificial intelligence is moving from literature
retrieval toward evidence synthesis for knowledge graphs, clinical decision support, and computational models. Yet most information-extraction systems still represent findings as simple relations, discarding the quantitative and contextual detail needed for interpretation and reuse. A claim that one entity affects another is insufficient when the magnitude, unit, population, comparator, experimental conditions, uncertainty, and provenance are missing. We define quantitative evidence mining as a framework for transforming biomedical findings into structured, context-rich, and auditable evidence units. We define the core elements of an evidence unit: the claim; measured entity and property; value, unit, or scale; comparator; population; biological or clinical conditions; temporal context; uncertainty; provenance; validation results; and expert-review status. We propose an eight-stage reference architecture spanning corpus selection, entity recognition, quantity extraction, context linking, normalization, evidence-unit assembly, multidimensional plausibility assessment, and export and governance. A central principle is that plausibility should not be collapsed into a single truth label; statistical, biological, methodological, contextual, and provenance-based support should remain explicit. The framework links information extraction to evidence synthesis and computational reuse, with applications in clinical-trial analysis, biomarker research, pharmacovigilance, knowledge-graph construction, and mechanistic modelling. It is a research agenda rather than a validated end-to-end system. Progress will require annotated
multimodal benchmarks, rigorous component- and workflow-level evaluation, prospective testing, transparent provenance, and sustained expert oversight.
Read the full abstract ▾
All authors Negin Sadat Babaiha, Stefan Geissler, Marie-Christine Simon, Martin Hofmann-Apitius, Marc Jacobs
Machine Learning
Foundation Models Meet Agriculture: Challenges Beyond Pretraining
Vishal Nedungadi, Xingguo Xiong, Marc Rußwurm et al. (+1 more)
Global food security and sustainable
climate action increasingly rely on robust, scalable agricultural monitoring. Earth observation foundation models have emerged as powerful, label-efficient tools across general remote sensing domains, yet early attempts to deploy them for agricultural applications have yielded surprisingly poor results. We hypothesize that this performance gap stems from the extreme heterogeneity of agricultural landscapes and the inherent inability of current earth observation foundation models to adapt to task-specific nuances. In this work, we systematically evaluate two critical bottlenecks hindering the deployment of foundation models in agricultural tasks, benchmarking two earth observation foundation models, a foundation model designed for tabular data, and conventional supervised baselines across seven real-world agricultural
datasets spanning yield prediction, phenology estimation, and crop classification. First, we identify a pretraining-deployment modality gap: agricultural downstream tasks frequently require diverse, non-imagery data modalities that earth observation foundation models are architecturally unequipped to ingest, while a foundation model built for tabular data handles this heterogeneity more naturally. Second, we formalize the agricultural task space across five structural axes to demonstrate why current models fail to generalize reliably, resulting in highly unstable model rankings across evaluation settings. By characterizing these structural and modal gaps, our insights highlight the friction between general-purpose architectures and specialized agricultural downstream data, providing a strategic roadmap for developing the next generation of domain-aware foundation models.
Read the full abstract ▾
All authors Vishal Nedungadi, Xingguo Xiong, Marc Rußwurm, Ioannis N. Athanasiadis