Artificial Intelligence · Cross-listed from cs.CL
Where Do Models Find Happiness? Emotion Vectors in Open-Source LLMs
Sinie van der Ben, Raphaël Baur, Yannick Metz et al. (+1 more)
Recent work identified
emotion vectors in Claude Sonnet 4.5, which are internal representations that encode
emotion concepts, causally influence behavior, and exhibit geometry mirroring human psychological structure. We test the generality of these findings in two open-weight models, Apertus-8B-Instruct-2509 and Gemma-4-E4B-it, extracting
emotion contrast vectors across all layers, using two model-generated corpora. We recover valence geometry for both models, with peak PC1–valence correlations of $r = 0.76$ and $r = 0.83$, approaching the $r = 0.81$ reported for Claude.Beyond replication, we observe notable differences in how valence representations emerge across model depth. In Gemma-4-E4B-it, valence is strongly encoded in early layers but collapses towards later layers, whereas Apertus-8B-Instruct-2509 exhibits the opposite pattern, with valence representations absent in early layers, but emerging at mid depths. Arousal encoding, in contrast, is sensitive to the extraction corpus: both models show stronger PC2–arousal
alignment with Gemma-generated stories ($r$ up to $0.45$) than Apertus-generated ones ($r \leq 0.21$), suggesting arousal-relevant cues are unevenly distributed across generated corpora. We open-source our experiment code and
dataset for reproducible investigation of
emotion representations across
language model architectures.
Read the full abstract ▾
All authors Sinie van der Ben, Raphaël Baur, Yannick Metz, Mennatallah El-Assady
Artificial Intelligence · Cross-listed from cs.CL
ReaORE: Reasoning-Guided Progressive Open Relation Extraction Empowered by Large Reasoning Models
Xin Lin, Liang Zhang, Guoqi Ma et al. (+2 more)
Open Relation Extraction (OpenRE) requires a model to extract unseen relations between head and tail entities from unstructured text for real-world applications. The core challenge of OpenRE lies in achieving reliable generalization to unseen relation types. Current OpenRE approaches either employ clustering techniques, which cannot generate relation labels and suffer from poor generalization, or rely on direct relation label generation via Large
Language Models (LLMs), which lack sufficient discriminative capacity to distinguish easily confused relations. To address these limitations, we propose
Reasoning-guided progressive OpenRE (ReaORE), a framework for performing relation extraction through coarse-to-fine relation
reasoning. Specifically, ReaORE consists of two key stages: (i) relation filtering, which reasons over multiple aspects to understand relations and instances, yielding an initial relation set, and further supplements and filters relations via
embedding-based similarity to ensure the target relation is included; (ii) relation prediction, which aims to predict the target relations from the above set via fine-grained comparative
reasoning to better distinguish easily confused relations. Extensive experiments on two widely used OpenRE
datasets demonstrate that ReaORE outperforms existing baselines.
Read the full abstract ▾
All authors Xin Lin, Liang Zhang, Guoqi Ma, Hongyao Tu, Jinsong Su
Artificial Intelligence · Cross-listed from cs.CL
Auditing Framing-Sensitive Behavioral Instability in Large Language Models for Mental Health Interactions
Abla Bedoui, Ashley L. Greene and Mohammed Cherkaoui
Large
language models (LLMs) are increasingly being integrated into mental health support tools and other psychologically sensitive conversational applications. In such settings, behavioral stability and consistency are important for trustworthy human-AI interaction. However, semantically similar concerns can be presented through different contextual framings, potentially eliciting different model responses. Such framing-sensitive variability may challenge user expectations regarding system behavior and complicate the assessment of AI reliability. While prior studies have primarily examined such effects at the behavioral level, less is known about how framing-related variation is reflected in the internal representations of aligned
language models. In this work, we investigate these effects using controlled matched
prompts spanning multiple contextual framing conditions across several instruction-tuned model families. Across architectures, framing systematically alters interpretive response tendencies. Layer-wise probing analyses show that behavior-associated information remains decodable throughout
transformer depth, with architecture-dependent variation in decoding strength. Moreover, held-out framing probes remained consistently above chance across architectures despite strong lexical baselines. Activation steering experiments further suggest that framing-associated representational directions can partially modulate downstream behavioral outcomes. Finally, these findings indicate that robustness to contextual variation may represent an important consideration when evaluating the consistency and trustworthiness of conversational AI systems deployed in mental-health-oriented interactions.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physics
Xiaomeng Fu, Junfan Lin, Yang Liu et al. (+4 more)
Synthesizing human motion from textual descriptions is essential for immersive digital applications, yet existing methods face a persistent trade-off between semantic fidelity and physical realism. Large
language model (LLM)-based approaches can interpret diverse open-vocabulary instructions and compose high-level action plans, but they often generate motions that violate physical constraints. Physics-aware models improve realism through simulation or control, but they struggle with semantic complexity, fine-grained instructions, and novel concepts. To address this gap, we propose In-Context Model Predictive Generation (ICMPG), a framework that integrates
language-model planning with inference-time physical feedback. ICMPG reformulates motion synthesis as a Model Predictive Control (MPC)-like process with two modules. The Context-Aware Motion Generation (CAMG) module uses an LLM as a planner to decompose textual commands and generate candidate motion sequences from motion
tokens. The Model Predictive Generation (MPG) module evaluates these candidates through physical simulation and semantic
alignment, estimates a composite reward, and selects the best sequence to guide subsequent generation steps. Unlike open-loop generation, this closed-loop refinement enables ICMPG to adapt motions to both the input semantics and the simulated physical environment without task-specific policy retraining. Extensive experiments across standard and zero-shot open-vocabulary settings show that ICMPG generalizes robustly to diverse commands and produces motions that are more physically plausible and semantically faithful than representative baselines on the evaluated
benchmarks. The framework bridges semantic interpretation and physical simulation while remaining flexible enough to incorporate different LLM backbones, enabling more versatile and controllable text-driven motion synthesis.
Read the full abstract ▾
All authors Xiaomeng Fu, Junfan Lin, Yang Liu, Yaowei Wang, Guanbin Li, Liang Lin, Ziliang Chen
Artificial Intelligence · Cross-listed from stat.ML
XMSE-Aware Adaptive Empirical Bayes Estimation
Minghao Chen and Jiale Zheng
Empirical Bayes (EB)
estimators can match the first-order asymptotic risk of maximum likelihood (ML) while behaving very differently at second order: recent excess mean squared error (XMSE) analysis shows that kernel-based EB estimation may be worse than ML when the kernel is poorly aligned with the true parameter. This paper turns that diagnostic into a design principle. We propose an XMSE-aware mixed
estimator that interpolates between ML and EB shrinkage. Its fixed-weight XMSE is a scalar quadratic, yielding a closed-form oracle mixing weight that is no worse than both ML and the base EB
estimator at the XMSE scale. A plug-in implementation based on finite-sample XMSE approximations is proved consistent, with a second-order oracle regret rate for an interior oracle weight. We further establish a transfer of the regret bound to the fixed-weight risk curve evaluated at the selected weight, a thresholded boundary rule, and extensions to compact kernel families and to finite and growing kernel dictionaries with high-probability oracle bounds. Finite impulse response simulations with SURE-tuned, hard-selection, and trace-corrected baselines, together with the public Silverbox and Cascaded Tanks
benchmarks, show that the proposed
estimator retains most of the benefit of regularization when it is helpful and retreats toward ML under kernel misspecification, with an identified finite-de analyzed on the
benchmarks.
Read the full abstract ▾
Artificial Intelligence
Einstein World Models
Munachiso Samuel Nwadike, Zangir Iklassov, Ali Mekky et al. (+2 more)
Does intelligence require the ability to reason about phenomena beyond direct experience? It is natural to suspect that some complex thought cannot be captured through
language alone. However, of particular concern to this work, is whether visualising counterfactual events can complement
language as a mechanism for complex thought. We ask whether LLMs can be trained to utilise such visualisation mechanisms, in a way that benefits their
reasoning abilities. Motivated by this question, we propose Einstein World Models. EWMs are a blueprint for LLM-based
reasoning systems that place visual-temporal rollouts inside the
reasoning trace, allowing them to reason in ways that text alone may not support well. In an EWM, the LLM calls a world-module (not to be confused with a world model), to produce short rollouts of scenes under consideration. The returned rollout is treated not as the answer, but as an inspectable hypothesis that can support later
reasoning. Einstein World Models extend the capability of LLMs for tool calling (such as web search or code execution), into the domain of visual thought experiments.
Read the full abstract ▾
All authors Munachiso Samuel Nwadike, Zangir Iklassov, Ali Mekky, Zayd M. Kawakibi Zuhri, Kentaro Inui
Artificial Intelligence
Look-Before-Move: Narrative-Grounded World Visual Attention in Dynamic 3D Story Worlds
Jiaming Bian, Bingliang Li, Yuehao Wu et al. (+5 more)
As
embodied AI and world models increasingly operate in dynamic 3D environments, visual perception must move beyond passively interpreting given observations toward actively deciding what to observe. We study this problem through camera planning in dynamic 3D story worlds, where the camera must not only generate smooth motion, but also decide what visual evidence should be acquired before it moves. We formulate this capability as Narrative-Grounded World Visual
Attention, where the camera acts as an
embodied observer that determines what to observe, how to compose the observation, and how to shift
attention over time under narrative intent and physical 3D constraints. To realize this capability, we propose Look-Before-Move, a camera planning framework that separates observation specification from motion execution. It first builds a Semantic Observation Contract to convert directorial intent into executable visual constraints, then performs Monte Carlo Viewpoint Search to find narrative-compliant and geometrically feasible viewpoints, and finally applies Semantic Trajectory Grounding to connect selected viewpoints into continuous, collision-aware, and temporally coherent camera motion. We further construct a dynamic 3D Story World
Benchmark based on StoryBlender, covering 50 stories, 457 scenes, and 1585 shots with animated characters, semantic scene configurations, and executable 3D environments. Experiments show that our framework improves subject perception, intent consistency, and trajectory quality over representative baselines, demonstrating the importance of organizing visual
attention before generating camera motion.
Read the full abstract ▾
All authors Jiaming Bian, Bingliang Li, Yuehao Wu, Pichao Wang, Zhi Wang, Hailan Ma, Huadong Mo, Zhenhong Sun
Artificial Intelligence · Cross-listed from cs.CV
Scaling Multi-Reference Image Generation with Dynamic Reward Optimization
Wenwang Huang, Yusen Fu, Junjie Wang et al. (+6 more)
While personalized image generation has achieved remarkable progress, multi-reference image generation (MRIG) remains a challenging task. Most existing
benchmarks fail to adequately evaluate complex MRIG scenarios, hindering further progress in this area. To better assess model performance on complex MRIG tasks, we introduce OmniRef-Bench, a
benchmark that covers complex combinations of reference image types and a large number of reference images. Evaluations on OmniRef-Bench show that mainstream open-source models struggle in complex MRIG scenarios, and their performance deteriorates significantly as the number of mixed-type reference images increases. To address this issue, we propose DyRef, a two-stage training framework. In the first stage, supervised fine-tuning equips the model with the basic capability to handle complex MRIG tasks. In the second stage, we introduce Difficulty-aware Advantage Reweighting (DAR) and Discriminative Reward Scaling (DRS). DAR dynamically adjusts the optimization objective to improve performance when handling a large number of mixed-type reference images. DRS enlarges intra-group reward differences for more effective policy optimization. Experiments demonstrate that DyRef significantly improves the performance of open-source models on OmniRef-Bench and single-image editing
benchmarks, demonstrating the effectiveness and generalization capability of our approach.
Read the full abstract ▾
All authors Wenwang Huang, Yusen Fu, Junjie Wang, Mengfei Huang, Yulin Li, Gan Liu, Jing Cai, Yancheng He, Zhuotao Tian
Artificial Intelligence
Where Do CoT Training Gains Land in LLM based Agents?
Jingyu Liu, Zhiwen Wang, Yuxin Jing et al. (+2 more)
Chain-of-thought (CoT)
reasoning is widely used in
language-model
agents, but prior work has shown that verbalized CoT is not always faithful and may instead reflect post-hoc
reasoning, which means the model already knows the answer before
reasoning. We therefore ask what CoT training is actually improving: is the model getting better at changing its action through generated
reasoning, or is it getting better at predicting the action directly from the
prompt? We study this question by comparing
prompt actions (predicting action without CoT) with CoT actions (predicting action with CoT). Across checkpoints,
prompt-action quality improves substantially. While interacting with the environment, the relative advantage of CoT actions over
prompt actions remains similar, showing that CoT training does not widen the advantage of CoT
reasoning, and it helps to improve the quality of
prompt actions. We further find that later checkpoints are less likely to revise the action in response to CoT, suggesting greater reliance on the
prompt. Motivated by these patterns, we selectively mask action-
token supervision on a fraction of training examples. This intervention improves out-of-domain generalization.
Read the full abstract ▾
All authors Jingyu Liu, Zhiwen Wang, Yuxin Jing, Huanyu Zhou, Yong Liu
Artificial Intelligence · Cross-listed from cs.CR
Chai: Agentic Discovery of Cryptographic Misuse Vulnerabilities
Corban Villa, Sohee Kim, Austin Chu et al. (+2 more)
AI-assisted vulnerability discovery has proven effective for bug classes like
memory safety, where instrumentation confirms
memory violations and efficiently filters false positives. Many dangerous vulnerability classes, such as cryptographic misuse, however, lack any comparable instrumentation. In this work, we present Chai, an AI-based system that discovers and validates cryptographic misuse vulnerabilities through naturally occurring signals. To achieve this, Chai rethinks the classical technique of differential testing by leveraging AI to 1) improve precision for detecting real security issues in libraries, and 2) repurpose commonly overlooked discrepancies as leads for tangible vulnerabilities in downstream applications. In doing so, Chai inverts the prevailing paradigm of AI vulnerability discovery: instead of
auditing one codebase for many flaws, it catalogs flaws at the library level and propagates them across a cryptographic dependency graph, delivering compounding efficiency gains. We evaluate Chai across X.509, JWT, and SAML libraries. Chai discovered a previously unknown critical vulnerability in an SSL library that powers billions of devices, along with security bugs in one library behind a major web browser and another in major Linux distributions. In total, these techniques surfaced over 100 vulnerabilities.
Read the full abstract ▾
All authors Corban Villa, Sohee Kim, Austin Chu, Alon Shakevsky, Raluca Ada Popa
Artificial Intelligence · Cross-listed from cs.SE
A Deterministic Control Plane for LLM Coding Agents
Padmaraj Madatha
LLM coding harnesses grant
agents broad file and shell access, yet the configuration layer that steers them – rules files,
agent definitions, IDE-specific markdown – is largely unmanaged. A prevalence study of 10,008 public GitHub repositories (n=6,145
agent config files) finds that
agent configurations propagate as undeclared shared components: 10.1% of tracked paths are SHA-256 exact duplicates across independent repositories (fork-adjusted, threshold-independent), with 75.5% of clone pairs crossing organisational boundaries. Two further patterns are indicative: configurations are rarely revised (58% single-commit; 0.4 vs 0.6 commits/month age-normalised against CI/CD workflows), and rarely declare permission boundaries (<1% of
agent configs vs 33% of Actions workflows, n=31 true positives). We propose a deterministic control plane above the harness that maps one-to-one to these gaps. Rel(AI)Build treats
agent definitions as a managed supply chain (SHA-256 content addressing, HMAC-stamped lockfiles, hash-chained audit logs); enforces tiered permissions and attack-derived blocklists before LLM invocation; gates feature work through a phase state machine with requirement-to-file-to-test traceability; compiles a single canonical definition to seven IDE targets; and detects
prompt drift via Jaccard similarity. Conformance tests on injected violations confirm each mechanism enforces its stated invariant; developer outcomes remain future work. Governance of this layer must be deterministic and tool-agnostic – not delegated to further LLM orchestration.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
Risk-Aware Selective Multimodal Driver Monitoring with Driver-State World Modeling
Daosheng Qiu, Haozhuang Chi, Hao Su et al. (+4 more)
Continuous driver monitoring in automated vehicles requires low-latency inference while avoiding unsafe decisions under uncertain driver states. Large
vision-
language models provide broad
multimodal priors, but their latency and limited reliability in this setting make them unsuitable as always-on in-cabin monitors. We propose a cost-aware selective inference framework for deployable
multimodal driver monitoring. The core system is a lightweight RGB-physiological student that combines in-cabin visual observations with window-level HR/EDA signals, and a learned gate that decides when to accept the fast prediction or abstain for safety intervention. Additional controls show that the learned scores contain sample-level information beyond scenario priors, while exact physiological synchronization remains a limitation. To incorporate predictive evidence, we further study a compact driver-state world modeling module that rolls out latent driver-state features and estimates future fast-model errors and counterfactual system-level action costs. On scenario-induced driver-demand recognition, the RGB-physiological student improves over RGB-only and physiology-only baselines, reaching 0.7440 Macro-F1 and 0.9099 balanced accuracy with 11.39M parameters and 3.08ms inference latency. Cost-aware selective inference reduces unsafe false negatives from 17.37% under always-fast inference to approximately 5% across seeds, while maintaining deployment-level latency. While driver-state world modeling offers valuable predictive signals, worst-group evaluations highlight persistent operating-point calibration drift. Ultimately, reliable edge driver monitoring requires advancing not only perception backbones, but also risk-aware selective control and group-robust calibration.
Read the full abstract ▾
All authors Daosheng Qiu, Haozhuang Chi, Hao Su, Shu Long, Xinyue Miao, Yongle Dong, Wei Zhang
Artificial Intelligence
Diagnosing Task Insensitivity in Language Agents
Jingyu Liu, Jiaen Lin, Xiaopeng Wu et al. (+3 more)
Language agents select actions based on task descriptions, environmental observations, and interaction histories. We investigate whether task requirements reliably constrain these decisions when the surrounding context already suggests how to proceed. Across five models and three interactive environments, we find that models, including GPT-5.6-Sol, can continue to act when task descriptions are replaced with the meaningless placeholder xxxx, even when prompted to ask for clarification. Action generation is more frequent in states that suggest a concrete next operation, although these cues do not establish whether that operation serves the user's goal. These findings suggest a possible training-based explanation: contextual cues can make demonstrated responses predictable, allowing models to fit them with limited reliance on task requirements. Tracking seven models during fine-tuning, we observe an overall decrease in
attention to task-description
tokens and an increase in
attention to current observations. To strengthen task dependence, we introduce Task-Perturbed Negative Log-Likelihood (TPNLL), which contrasts the prediction costs of the same response under different task descriptions while holding the non-task context fixed. TPNLL increases
attention to task-description
tokens and improves complete-episode success in out-of-distribution settings.
Read the full abstract ▾
All authors Jingyu Liu, Jiaen Lin, Xiaopeng Wu, Kehan Chen, Chuan Yu, Yong Liu
Artificial Intelligence · Cross-listed from cs.LG
GEOALIGN: Geometric Rollout Curation for Robust LLM Reinforcement Learning
Ting Zhou, Zhenqing Ling, Yiyang Zhao et al. (+2 more)
Online reinforcement learning is widely used to align large
language models (LLMs) with reward signals, yet training can be unstable under noisy or misspecified rewards. We identify a failure mode we call directional inconsistency: within a batch, a small set of high-reward rollouts induces representation-space preference directions that sharply disagree with the batch majority, resulting in high-variance and destabilizing updates. We propose geoalign, a lightweight plug-in for rollout curation in iterative policy optimization. Geoalign (i) forms within-
prompt preference pairs, (ii) learns an online projector on per-rollout hidden states to concentrate reward-ordered displacement directions, and (iii) detects directionally inconsistent rollouts via their angular deviation from a batch consensus prototype and rectifies them with within-
prompt stable alternatives. Geoalign is forward-pass only and adds negligible overhead. Across dialogue
alignment with a learned reward model and mathematical
reasoning with binary verified rewards, Geoalign improves final performance and reduces training oscillation, outperforming PF-PPO, PAR, PODS, and Seed-GRPO. These results suggest latent directional consensus as an effective reliability signal for online LLM RL.
Read the full abstract ▾
All authors Ting Zhou, Zhenqing Ling, Yiyang Zhao, Ying Shen, Daoyuan Chen
Artificial Intelligence · Cross-listed from cs.CV
Confidence-Aware Tool Orchestration for Robust Video Understanding
Yangfan He, Yujin Choi and Jaehong Yoon
Video reasoning language models implicitly assume that every input frame is equally reliable. This leads to what we term the Blind Trust Problem: under realistic perturbations such as motion blur, glare, or occlusion, frontier
video reasoning models can suffer 15-30%p accuracy drops on real-world
embodied benchmarks, while remaining unaware that their visual evidence has been degraded. To address this challenge, we propose Robust-TO, an agentic
video understanding framework that explicitly integrates per-frame trustworthiness into every stage of
reasoning. Robust-TO organizes heterogeneous visual perception tools under a unified evidence interface. Each tool receives a sub-query derived from the original question and a set of trustworthy frames selected by the reliability-relevance score. It returns evidence in a shared format: a concrete prediction (e.g., a bounding box, motion trajectory, recognized text, or action label), temporal grounding, and a calibrated reliability score. During
reasoning, these calibrated scores guide evidence weighting in a three-tier synthesis process (high/medium/low) and define a confidence-cost GRPO reward that jointly optimizes correctness, evidence reliability, and efficiency. On two
video reasoning benchmarks spanning eight tasks, Robust-TO achieves 56.4% average accuracy on clean inputs, surpassing the strongest open-source baseline by 10.6%p and outperforming Gemini-2.5-Pro (46.2%). Under five realistic corruption types, Robust-TO maintains 54.3% average accuracy, 5.8%p above the strongest open-source baseline, while exhibiting the smallest clean-to-corrupted accuracy drop among all compared methods.
Read the full abstract ▾
Artificial Intelligence
Learning to Recover Task Experts from a Multi-Task Merged Model
Jinwook Jung, Taegyu Kim, Kumju Jo et al. (+1 more)
Multi-task model merging aims to consolidate several task-specific experts into a unified model, yet static merging consistently suffers from parameter interference. While dynamic merging models aim to bridge this gap, many works rely on the costly storage and loading of redundant expert components at inference. In this work, from the perspective of task expert, we view parameter interference as parameter perturbation introduced to each expert during merging process. We show that such parameter perturbations can be modeled as affine transformation, which can be approximated as additive offsets. Motivated by these, we propose Recover Task eXpert (ReTeX), a framework that predicts those offsets, in order to undo parameter interference and recover task-expert performance from a single merged checkpoint. To recover the appropriate expert when task identity is unknown, we introduce a router-free task identifier based on SVD subspace signatures computed offline before inference. At inference, the identifier selects the task whose subspace yields the smallest projection residual for a given input. As a result, ReTeX recovers over 95% of individual-expert performance in both
vision and NLP domains, while significantly improving generalization to unseen tasks. Crucially, we also show that the parameter offset prediction leads to emergent adaptive interpolation of expert knowledge for out-of-distribution (OOD) tasks. ReTeX adaptively interpolates seen expert knowledge to handle unseen tasks. Our code is available at https://github.com/BAIKLAB/ReTeX
Read the full abstract ▾
All authors Jinwook Jung, Taegyu Kim, Kumju Jo, Sungyong Baik
Artificial Intelligence · Cross-listed from cs.CL
Subham Kumar, Prakrithi Shivaprakash, Abhishek Manoharan et al. (+7 more)
Automatic
Speech Recognition (ASR) is increasingly used to document clinical encounters, yet its reliability in
multilingual and demographically diverse Indian healthcare context remains largely unknown. In this study, we first conduct the systematic audit of ASR performance on real-world psychiatric interview data spanning Kannada, Hindi and Indian English, comparing eight state-of-the-art models including IndicWhisper, WhisperLargeV3, Sarvam, GoogleS2T, Gemma3n, OmniLingual, Vaani, and Gemini. Our results reveal substantial variability across models and
languages, with some systems performing competitively in Indian English but failing in regional
speech. We further fine-tune two of the best performing opensource models, i.e., Gemma3n and OmniLingual, using various methods. With this, we uncover systematic performance gaps tied to speaker role and gender, raising concerns about equitable deployment in clinical settings, which are further mitigated by
fairness-aware fine-tuning. To this end, we propose SamaVaani, a unified debiasing technique that simultaneously improves ASR performance and improves
fairness across demographic groups.
Read the full abstract ▾
All authors Subham Kumar, Prakrithi Shivaprakash, Abhishek Manoharan, Astut Kurariya, Diptadhi Mukherjee, Prabhat Chand, Pratima Murthy, Koustav Rudra, Lekhansh Shukla, Animesh Mukherjee
Artificial Intelligence
MORPH: Generative Retrieval via Diffusion Transformer with Metric-Ordered Sequence Training and Hybrid-Policy Preference Optimization
Chenghao Liu, Yu Zhang, Zhongtao Jiang et al. (+8 more)
Embedding-based
retrieval typically returns highest-scoring items, but many production scenarios require items that satisfy a target attribute while preserving a fine-grained pattern expressed by seed examples. We formalize this as pattern-preserving attribute
retrieval. Standard approaches fail: averaging seeds preserves the pattern but misses the attribute; global attribute
retrieval drifts to unrelated patterns. We approach the task with continuous generative
retrieval, where a model reads item-
embedding sequences and generates query
embeddings for nearest-neighbor search. We propose MORPH: Generative
Retrieval via
Diffusion Transformer with Metric-Ordered Sequence Training and Hybrid-Policy Preference Optimization, a staged framework with large-scale raw-sequence pretraining, Metric-Ordered Sequence (MOS) training, and final HPPO
alignment. MOS construction turns sparse online metric labels into in-pattern trajectories; MOS CPT/SFT then trains the generator through shared multi-domain continuation pretraining and domain-specific tail-centroid supervised fine-tuning. HPPO uses a hybrid pool of static and policy-generated candidate
embeddings, labels them with true online intersection metrics, applies iterated preference optimization, and employs a Pareto pair filter to exclude winners that lower pattern purity. Across four large-scale attribute domains under strict item- and pattern-holdout protocols, MOS training improves the primary intersection metric over a strong pretrained generative retriever in every domain-split
cell, and the complete Pareto-filtered HPPO procedure improves it further, with paired-bootstrap-significant gains on seven of the eight
cells - the exception being the D4 pattern-holdout split. Ablations confirm that the Pareto pair filter improves the attribute-pattern tradeoff on D1-D3, and that hybrid static/policy candidates are complementary.
Read the full abstract ▾
All authors Chenghao Liu, Yu Zhang, Zhongtao Jiang, Kun Xu, Zhenwei An, Renzhi Wang, Zhao Wang, Jiachen Zhang, Yuxiao Zhang, Kun Xu, Songfang Huang
Artificial Intelligence · Cross-listed from cs.CV
Bridging Vision and Language Concepts through Optimal Transport Semantic Flow
Chenyang Zhang, Anqi Dong, Guangming Zhu et al. (+4 more)
Concept Bottleneck Models (CBMs) promise transparent
reasoning by predicting through human-interpretable concepts, yet their effectiveness fundamentally depends on how well visual and textual representations are aligned or matched. Existing
vision-
language CBMs often rely on pre-aligned encoders or global cosine similarity, which obscures fine-grained concept localization and fails to reflect true semantic geometry. In this work, we rethink concept
alignment as a dynamic cross-modal transport process instead of static projection and propose the Optimal Transport Flow Concept Bottleneck Model (OTF-CBM). It first learns a data-driven semantic cost via Inverse Optimal Transport to measure cross-modal distances, and then performs unbalanced optimal-transport-based flow matching to model semantic transitions between visual patches and textual concepts. With velocity-based concept activation, OTF-CBM captures interpretable
geometric relations without ODE integration. Experiments further show that OTF-CBM achieves superior classification accuracy and concept faithfulness, offering a new
geometric and dynamical perspective for interpretable cross-modal
reasoning.
Read the full abstract ▾
All authors Chenyang Zhang, Anqi Dong, Guangming Zhu, Nuoye Xiong, Siyuan Wang, Lin Mei, Liang Zhang
Artificial Intelligence
A Pipeline for Generating Longitudinal Synthetic Clinical Notes Using Large Language Models
William Poulett, Alice Waterhouse, Ben Wallace et al. (+4 more)
Synthetic data is increasingly used to enable the development and evaluation of AI systems in domains where access to real-world data is restricted. In healthcare, clinical documentation presents particular challenges due to its sensitivity. This work introduces a synthetic clinical notes pipeline and
dataset designed to support the development of clinical AI tools while avoiding the
privacy risks associated with real patient data. The
dataset is generated using a modular pipeline that combines structured patient generation, semi-structured patient journey simulation, and unstructured clinical note generation using large
language models. The pipeline is designed to prioritise internal consistency across longitudinal patient records, while also capturing variation in writing style, note structure, and clinical detail. Additional mechanisms, including LLM-based validation and augmentation steps, are used to improve faithfulness, realism, and diversity of the generated notes. We release a
dataset of 70 synthetic patients, each associated with 20-50 clinical notes spanning a full hospital journey. The
dataset is provided at multiple levels of validation, enabling users to balance realism and scalability depending on their use case. This
dataset supports the development, testing, and evaluation of clinical AI systems, including summarisation tools, coding models, and decision support systems, without reliance on real patient data.
Read the full abstract ▾
All authors William Poulett, Alice Waterhouse, Ben Wallace, Scarlett Kynoch, Amaia Imaz Blanco, Michael Spence, Jonathan Pearson
Artificial Intelligence · Cross-listed from cs.CL
Information-Aware KV Cache Compression for Long Reasoning
Jushi Kai, Zhuiri Xiao, Alexandra Birch et al. (+1 more)
Reasoning capability has advanced rapidly in large
language models (LLMs), leading to an increasing size of key-value (KV) cache in both prefilling and decoding stages. Existing KV cache compression methods mainly rely on
attention weights to estimate
token importance. While
attention effectively captures contextual relevance, it overlooks complementary information-theoretic signals related to predictive uncertainty and
token informativeness. In this paper, we revisit
token importance from a forward-looking perspective and introduce Forward Influence, a metric that measures how compressed
tokens affect future contexts. Our analysis reveals that
tokens selected by
attention scores mainly influence nearby contexts, whereas
tokens associated with high predictive uncertainty exhibit substantially stronger influence on distant future contexts. Based on the observation, we propose InfoKV, an
entropy-aware KV cache compression framework that incorporates information-theoretic signals. It combines
token-level predictive uncertainty with layer-wise representation
evolution and integrates the resulting
entropy scores with
attention scores during
reasoning. Experiments on long-context
reasoning benchmarks with Llama-3.1, Llama-3.2, and DeepSeek-R1 demonstrate that InfoKV consistently outperforms existing
attention-based KV compression methods in both long prefilling and decoding scenarios.
Read the full abstract ▾
All authors Jushi Kai, Zhuiri Xiao, Alexandra Birch, Zhouhan Lin
Artificial Intelligence
TAVR-VLM: Risk-Conditioned Causal Grounding for Hallucination-Resistant Report Generation
Zhixiang Lu, Xiwei Liu, Sifan Song et al. (+5 more)
Transcatheter Aortic Valve Replacement (TAVR) planning requires meticulous
multimodal reasoning. However, adapting
Multimodal Large
Language Models (MLLMs) to this high-stakes domain is severely impeded by diagnostic
hallucinations, where generated text lacks anatomical grounding. To address this, TAVR-VLM is introduced: a novel framework featuring Risk-Conditioned Causal Grounding
Attention (R-CGA) that instantiates a model-internal “Risk $\rightarrow$ Region $\rightarrow$ Word” structural grounding pathway. R-CGA compresses
multimodal inputs into a causal risk bottleneck, purifying dense visual features into a global risk mask. During autoregressive generation, a support-projected causal consistency objective constrains
token-level grounding within the risk-defined support mask. Evaluated on $\text{M}^3\text{TAVR}$, a comprehensive 1,482-patient cohort, TAVR-VLM establishes a new state-of-the-art. It achieves an AUROC of 0.896, boosts CIDEr to 0.936, and drastically reduces the
hallucination rate to 8.1%, thereby improving interpretability for evidence-based
surgical AI.
Read the full abstract ▾
All authors Zhixiang Lu, Xiwei Liu, Sifan Song, Changkai Ji, Anh Nguyen, Jionglong Su, Imran Razzak, Jinfeng Wang
Artificial Intelligence · Cross-listed from cs.CR
Fortress and Gatekeeper: Theorizing Transitive Trust in Third-Party Cybersecurity Risk Governance
Yijun Chen and Misita Anwar
Third-party vendors, such as analytics platforms, cloud services, identity providers, and software suppliers, are increasingly embedded in digital service delivery. While these arrangements enable scale and specialization, they also move customer data and security-relevant practices into environments that customers rarely see, select, or evaluate. This paper examines this problem through a document analysis of the November 2025 OpenAI-Mixpanel security incident. The incident serves as an illustrative case for showing how a security event in a vendor environment can become a governance and accountability problem for the focal organization that maintains the customer relationship. Drawing on organizational trust research and agency theory, the paper argues that third-party cybersecurity risk is both a trust relationship and a delegation problem. Customers trust the visible service provider, while the provider relies on vendors whose security practices are only partially visible and controllable. The paper develops the concept of transitive trust, where customer trust in a digital service depends on the security practices of vendors authorized by that service provider. It then presents the Fortress and Gatekeeper framework, which explains cybersecurity governance boundaries through trust and data flows rather than formal organizational ownership alone. The analysis develops four propositions concerning vendor integration, metadata exposure, vendor assurance, and data proliferation. The paper contributes to cybersecurity governance scholarship by explaining how delegated data processing creates customer-facing accountability and by identifying implications for vendor tiering, data classification, contractual design, continuous assurance, and data minimization.
Read the full abstract ▾
Artificial Intelligence
AgentX: Towards Agent-Driven Self-Iteration of Industrial Recommender Systems
Changxin Lao, Fei Pan, Guozhuang Ma et al. (+59 more)
Recommendation
algorithm iteration is moving from an artisanal, engineer-bound process toward an industrialized research loop, but this transition remains blocked by a structural execution bottleneck: the idea-to-launch cycle still depends on human engineers to generate hypotheses, modify production code, launch A/B experiments, and attribute online results. Innovation therefore scales linearly with headcount rather than compounding with evidence, compute, and accumulated experimental knowledge. We present AgentX, a production-deployed multi-
agent system that fundamentally restructures this production function. AgentX operates as a self-evolving development engine: it autonomously generates, implements, evaluates, and learns from recommendation experiments at a scale and pace that no manual workflow can sustain. The system orchestrates four tightly coupled stages in a closed loop. A Brainstorm
Agent synthesizes evidence from historical experiments, system architecture, data analysis, and external research into ranked, executable proposals. A Developing
Agent translates each proposal into production-ready code through repository-grounded generation and multi-dimensional reliability verification. An Evaluation
Agent conducts safe online rollout with guardrail-vetoed A/B judgment, converting both successes and failures into structured knowledge assets. A Harness
Evolution layer (SGPO) then distills execution trajectories into semantic-gradient updates that continuously sharpen the
agents themselves – making the system not merely automated, but self-improving.
Read the full abstract ▾
All authors Changxin Lao, Fei Pan, Guozhuang Ma, Han Li, Huihuang Lin, Jijun Shi, Kangzhi Zhao, Kun Gai, Mo Zhou, Qinqin Zhou, Quan Chen, Ruochen Yang, Shifu Bie, Shijie Yi, Shuang Yang, Shuo Yang, Wenhao Li, Wentao Xie, Xiao Lv, Xuming Wang, Yijun Wang, Yiming Chen, Yusheng Huang, Zhongyuan Wang, Zibo Zhao, Zijie Zhuang, Baoning Xia, Chao Liu, Chaoyi Ma, Chubo He, Dawei Cong, Feng Jiang, Gang Wang, Guilin Xia, Hanwen Xu, Jiahong Xie, Jiahui Qiao, Jian Liang, Jiangfan Yue, Jing Wang, Jinghan Yang, Jinghui Jia, Kan Qin, Lei Wang, Ming Li, Peilin Song, Pengbo Xu, Qiang Luo, Ruiming Tang, Shiyang Liu, Shuxian Jin, Tao Wang, Tao Zhang, Xiang Gao, Xianghan Li, Yingsong Luo, Yiwen Ning, Yongcheng Liu, Yueyang Liu, Yuan Guo, Zhaojie Liu, Zhenkai Cui
Artificial Intelligence
LCAi: Life Cycle Assessment with big data fusion and retrieval-augmented generation-assisted interpretation
Georgios Tsironis, Juan D. Medrano-Garcia and Gonzalo Guillen-Gosalbez
The interpretation phase of life cycle assessment often lacks structured mechanisms for translating quantified improvement opportunities addressing environmental hotspots into actionable strategic pathways under technological, social, and policy uncertainty. To overcome this limitation, this study introduces a perspective-conditioned
retrieval-augmented generation framework for LCA interpretation, where a multi-perspective
retrieval and controlled synthesis is incorporated in the artificial intelligence (AI)-assisted LCA. To operationalise large
language models in LCA interpretation, a perspective fusion RAG architecture was developed, covering academic, industry, public discourse, and European union (EU) funding
datasets. Our approach comprises three steps: (1) a scenario anchor defining system boundaries and decarbonization targets, (2) a set of perspective-specific micro-queries with constrained
retrieval, and (3) a neutral synthesis step integrating only ledger-stored outputs without further
retrieval. The framework is demonstrated through a hydrogen-enabled diesel reduction use case in an Italian apple production facility using GPT-5 nano as the
reasoning model. Overall, the structured
retrieval and constrained synthesis are designed to mitigate the risk of
hallucination while preserving cross-domain diversity. The approach presented can support more disciplined translation of impact results into strategic pathways and opens up new avenues for the use of advanced AI tools in LCA studies, particularly those focused on technologies that could be deployed at scale. This proof-of-concept demonstrates how AI-assisted, evidence-grounded interpretation can support implementation-oriented decision-making beyond conventional LCA studies.
Read the full abstract ▾
Artificial Intelligence
Context-Aware Synthesis of Optimization Pipelines for Warehouse Optimization
Janik Bischoff, Anne Meyer, Uta Mohring et al. (+6 more)
Order fulfillment in manual picker-to-goods warehouses involves interconnected decisions such as item assignment, order batching, and picker routing. While integrated models capture interactions between these decisions, practical warehouse systems often require decomposed approaches due to organizational boundaries, differing responsibilities, or limited data availability. Existing studies primarily evaluate
algorithms for isolated subproblems or fixed subproblem combinations for specific warehouse settings, but lack a general mechanism to determine applicable
algorithm configurations, compose them into valid solution pipelines, and assess their performance. With Context-Aware Synthesis of Optimization Pipelines (CASOP), we propose a framework for constructing and evaluating context-specific optimization pipelines and apply these to order fulfillment. The framework comprises: (1) a modular repository of
algorithms for common order fulfillment problems; (2) semantic data and
algorithm cards to describe warehouse context and
algorithm requirements; (3) a taxonomy that structures order fulfillment problems into relevant subproblems; (4) a pipeline synthesizer that identifies applicable
algorithms for a given warehouse context and composes all valid optimization pipelines; and (5) a pipeline evaluator that assesses all resulting pipelines. We demonstrate the framework on 7
benchmark instance sets covering four problem classes, resulting in 1,063,044 valid pipelines. The framework supports researchers and practitioners in designing, automatically synthesizing, and selecting valid, high-performing algorithmic pipelines for warehouse operations. The software is open-source and available at https://github.com/kit-dsm/ware_ops_pipes and https://github.com/kit-dsm/ware_ops_algos. Keywords: Warehouse optimization,
Algorithm selection, Pipeline synthesis, Order fulfillment
Read the full abstract ▾
All authors Janik Bischoff, Anne Meyer, Uta Mohring, Fabian Dunke, Maximilian Barlang, Özge Nur Subas, Hadi Kutabi, Stefan Nickel, Kai Furmans
Artificial Intelligence
The Capability Frontier: Benchmarks Miss 82% of Model Performance
Bradley Fowler, Ryan Smith, Daniel Thi Graviet et al. (+8 more)
Existing
benchmarks typically report accuracy for a single model on a single run. This systematically understates real-world LLM capabilities, particularly under heterogeneous data distributions: (i) different models get different questions correct according to their specializations, and (ii) given a budget, multiple generations can be sampled and selectively retained. To quantify this gap, we introduce the Capability Frontier: a Pareto frontier over a set of models that characterizes the best achievable performance at each cost level under optimal selection across models and generations (i.e., via an oracle). Our construction corrects for two opposing biases: underestimation from single-model evaluation and overestimation from taking maxima over noisy samples. We study 21 LLMs across 16 widely used
benchmarks spanning coding,
reasoning, medicine, factuality, instruction following, and agentic tasks, comparing Capability Frontier performance at matched cost to each
benchmark's top-performing model. Correcting for single-model evaluation yields a 54% error rate reduction; additionally correcting for single runs yields an 82% improvement, with SOTA accuracy matched at 85% cost reduction. Complementing these empirical results, we use controlled probabilistic simulations to show that higher query topic
entropy produces a near-monotonic increase in the performance gap between oracle routing and the best single model. Our findings suggest collective LLM capabilities are substantially underestimated, with implications for evaluation and deployment in data-heterogeneous, multi-domain settings.
Read the full abstract ▾
All authors Bradley Fowler, Ryan Smith, Daniel Thi Graviet, William Myers, Joshua Greaves, Narmeen Fatimah Oozeer, Antía García, Philip Quirke, Amirali Abdullah, Fazl Barez, Shriyash Kaustubh Upadhyay
Artificial Intelligence
Computational Analysis of Heart Rate Variability in Healthy Adults
María J. Lado, Arturo J. Méndez, Leandro Rodriguez-Liñares et al. (+4 more)
Heart Rate Variability (HRV) analysis is a key indicator of cardiac physiological state and aids in disease diagnosis. However, research on HRV parameters in healthy individuals remains limited, and no gold standard exists. This study evaluates HRV indices in 40 healthy adults (20 men, 20 women, aged 30-50) to improve HRV's clinical utility. Using computational methods for signal processing and data analysis, time, frequency, and nonlinear indices were analyzed to address five questions: (1) normality, (2) stability, (3) correlation, (4) reproducibility, and (5) consistency. Key findings: (1) Time-domain and nonlinear indices, particularly global and LF (low frequency), follow normal distributions, with gender differences noted. (2) Most indices are stable except HF (high frequency)-related ones. (3) High correlations in HF-related indices suggest redundancy, indicating only one is necessary in studies. (4) Comparisons with the Fantasia database revealed less than 10% error for most indices, except SD2 and SDNN in women (greater than 15%). (5) Time-domain and nonlinear indices show low inter-study variability, while frequency-domain indices exhibit high variability, limiting cross-study comparisons. The selected indices-ApEn and IRRR (global variability), HRVi and SD2 (LF), and MADRR or rMSSD (HF)-are best suited for accurately representing HRV components and enhancing its clinical and research relevance.
Read the full abstract ▾
All authors María J. Lado, Arturo J. Méndez, Leandro Rodriguez-Liñares, Baltasar García Pérez-Schofield, Pedro Cuesta-Morales, Brais Iglesias-Otero, Xose A. Vila
Artificial Intelligence
KARLA: Knowledge-base Augmented Retrieval for Language Models
Francois Crespin, Fabian M. Suchanek and Nils Holzenberger
We propose a new method that allows an LLM to automatically pull in factual knowledge from a knowledge base during
token generation. This means that (1)~factual knowledge in the LLM output can be updated without retraining the LLM, (2)~facts in the LLM output can be traced to the knowledge base for transparency and explainability, and (3)~smaller models can achieve the same factual accuracy as larger models. Our core idea is to train the model to produce special
tokens that trigger a query to the knowledge base. Our experiments show that our method improves factual grounding in both short and long-form generation, and allows factual revisions to take effect through KB edits rather than parameter updates.
Read the full abstract ▾
Artificial Intelligence
Memory Depth, Not Memory Access: Selective Parametric Consolidation for Long-Running Language Agents
Haoliang Han
Long-running
language agents need more than
memory access.
Retrieval systems can fetch past facts at query time, but they do not decide which experiences should continue to shape behavior after the working context is unloaded. We study this separate problem as
memory depth: durable goal-conditioned tendencies written into a small parametric store. We introduce the loop-drift protocol, a controlled stress test in which the
retrieval index remains intact while working context is unloaded and goal-conditioned behavior must persist under long-loop interference. We evaluate EVAF, a surprise- and valence-gated LoRA consolidation mechanism. Across GPT-2 and TinyLlama,
retrieval is strongest on shallow factual recall (short-fact accuracy 0.956–0.973), while EVAF is strongest on goal persistence and post-unload recovery (0.812–0.904) with only 2–3 parametric writes per 200 events. Mechanism controls show that selective consolidation factorizes into two controllable dimensions: selection and actuation. Matched random gates isolate selection beyond sparse writing; fixed-inner controls across GPT-2, TinyLlama, and Mistral-7B show that inner-loop write strength is model-dependent; and a Mistral-7B matched-gate inversion reveals asymmetric selection-actuation coupling under miscalibrated actuation. Public Memora event streams serve as an external diagnostic, exposing stale-
memory invalidation as an unresolved boundary. Within this probe, selective parametric consolidation supplies
memory depth distinct from and complementary to
retrieval access.
Read the full abstract ▾