Papers

Diffusion Large Language Models (dLLMs) offer a promising avenue for parallel generation but face a trade-off between decoding speed and quality. While revocable decoding strategies attempt to mitigate errors by verifying and remasking tokens, they typically operate within a mixed-quality context. This leads to two critical failures: Error Propagation, where new tokens absorb toxic information from erroneous context, and Local Error Reinforcement, where errors mutually reinforce each other to evade detection. To alleviate these challenges, we propose ASRD (Anchor Supervised Revocable Decoding), a training-free framework that operates within the embedding space. ASRD explicitly decouples the decoding context into trusted Anchor Tokens, which are identified via temporal consistency, and uncertain candidates. Leveraging a dynamic Anchor Tokens Cache, we introduce two complementary mechanisms: (1) Anchor-Guided Generation, which injects entropy-weighted anchor signals into masked positions to implicitly rectify attention toward the reliable global skeleton; and (2) Anchor-Perturbed Verification, which applies orthogonal perturbations to uncertain candidate tokens, destabilizing and remasking errors driven by fragile local consensus. Extensive experiments on math and coding benchmarks demonstrate that ASRD outperforms recent remasking baselines, achieving accuracy improvements of up to 6.4% while accelerating inference throughput by up to 7.2$\times$.The code is available at https://github.com/preordinary/ASRD.

We study the operator-theoretic core of Q-learning in continuous-time stochastic control with continuous states and actions. In value-based reinforcement learning, each Q-learning or DQN update is built from a Bellman optimality target; our analysis isolates this target in a diffusion setting and studies its regularity and approximation complexity. Under uniform ellipticity and Hölder-regular coefficients, we show that a Bellman update maps bounded inputs into an anisotropic regularity class, smoothing the state variable while leaving only Lipschitz dependence on the action variable. This yields a compact family of Bellman iterates and motivates a tensor-product DeepONet architecture adapted to the mixed regularity of the problem. We then derive explicit approximation and resource bounds, together with a stiffness–complexity trade-off as the time step $\delta \to 0$. The resulting theory makes a direct contribution to Q-learning theory at the level of Bellman target regularity and approximation in continuous stochastic control. At the same time, we do not claim a full convergence theorem for practical sampled Q-learning with exploration, replay, and stochastic gradient updates.

Small-scale Large Language Models (LLMs) natively default to literal semantic interpretations, making few-shot irony detection a persistent challenge in noisy, user-generated text. In this study, we show that, despite this limitation, inference from compact LLMs can still be effectively harnessed for this task. We introduce the Robust Dual-Signal (RDS) Fusion framework, a hybrid neuro-symbolic architecture that utilizes a compressed Chain-of-Thought (CoT) of an LLM, alongside a static, pretrained RoBERTa and a symbolic prior module in two downstream fusions. RDS Fusion demonstrates better performance than an unrestricted reasoning ablation, while requiring substantially lower inference time. We also find that in our experiments, unrestricted reasoning does not yield better results than restricted reasoning. Evaluated on a strictly held-out TweetEval test set ($N=734$), RDS Fusion achieves $78.1\%$ accuracy and a Macro F1 of $0.777$, which is comparable to a finetuned BERTweet-base. On the heavily imbalanced iSarcasm dataset, the frozen CoT pipeline suppresses $22.5\%$ of baseline false positives, yielding a Macro F1 of $0.6726$ and Ironic F1 of $0.4821$, outperforming multiple heavily supervised SemEval transformer ensembles. Paired McNemar's tests show that, while adding the symbolic prior to the neural baseline yields an insignificant gain, and the RDS Fusion is statistically insignificant compared to the combined RoBERTa and symbolic prior ablation; the concurrent fusion achieves a statistically significant improvement over the standalone baseline ($p=0.005$).

Teaching Software Engineering for AI-enabled systems entails addressing the integration of AI components within full-scale software architectures under realistic constraints. While machine learning courses emphasize model development, students often lack experience in architectural design, deployment, and monitoring of AI-enabled systems. Empirical evaluations of such system-oriented AI courses remain limited. This paper reflects on the design and implementation of a project-based master's-level course titled AI Algorithms: Theory and Engineering, at the University of Bremen, in which students developed a movie recommendation system while making architectural design decisions to address challenges related to scalability, deployment, and evolving requirements. We conducted a mixed-methods study combining analyses of student submissions and questionnaire responses to investigate integration challenges, learning outcomes, and opportunities for improvement. Our results indicate persistent difficulties in early architectural decisions, heterogeneous ML integration, evolving requirements, and data management, largely due to uneven ML and software engineering expertise. From the educator's perspective, the course fostered system-level reasoning and strengthened awareness of data-centric ML practices in AI-enabled systems.

Spoofed speech detection is increasingly challenged by realistic synthesis, voice conversion, and replay attacks, with cross-dataset generalization remaining a major limitation. This work we propose a Temporal Pyramid Adapter that utilize parallel temporal convolutions with varying receptive fields to capture multi-scale spoofing cues, ranging from local artifacts to global prosodic irregularities. We also integrated self-supervised XLS-R representations combined with front-end adapters, including Mel, Sinc, and a Temporal Pyramid design for multi-scale temporal modeling. The proposed model is evaluated cross multiple benchmark including ASVspoof 2017, ASVspoof 2021 (DF/LA), PartialSpoof, DiffSSD, and multilingual HQ-MPSD datasets. Experimental results demonstrate that Temporal Pyramid model obtained AUC of 99.24% and a EER of 3.87% on the PartialSpoof database, which is significantly outperforming the base model and several SOTA baseline such as LCNN-BLSTM (9.87% EER) and TRACE (8.08% EER). Additionally, multilingual evaluations confirm that while spoofing artifact are independent from language. While self-supervised representations improve robustness, performance degrades under domain and language shifts, highlighting the need for better adaptation and calibration strategies.

Generalist manipulation policies are increasingly presented as foundation models for robotic control, but their real-world generalization remains difficult to diagnose. A policy may succeed on demonstrated tasks while still failing to execute fine-grained atomic skills or recombine learned skills in new task structures. We introduce ATOM-Bench, a real-world benchmark for evaluating both atomic skills and compositional generalization in manipulation policies. ATOM-Bench factorizes tabletop manipulation into motor atoms and instruction atoms, and contains 30 atomic tasks and 24 held-out compositional tasks across paired single-arm and dual-arm robot tracks. We collect 3,000 human demonstrations for atomic fine-tuning and release both the demonstration data and evaluation rollout data to support reproducible real-world evaluation. Policies are fine-tuned on atomic tasks and evaluated on both atomic skill acquisition and held-out compositional tasks. We further introduce Atomic Score (AS) and Compositional Failure Share (CFS) to distinguish failures caused by weak atomic skills from failures caused by limited compositional reuse. Through 2,700 physical rollouts on five representative manipulation policies, we find that current policies can acquire simple instruction-grounding skills, but still struggle with fine-grained motor atoms, counting, and logical filtering. More importantly, strong atomic performance does not reliably transfer to held-out compositional tasks. ATOM-Bench provides a diagnostic testbed for studying whether failures arise from weak motor execution, poor instruction grounding, or limited compositional reuse.

Mixture-of-Experts (MoE) architectures efficiently scale Large Language Models (LLMs) by activating only a small fraction of their experts per token, yet the full parameter count - dominated by the expert parameters - must be held in training and inference memory. To address this, we introduce Expert Tying, an architectural modification that shares expert parameters across consecutive transformer layers while preserving independent, layer-wise routing and attention. We evaluate this approach across common, state-of-the-art architectures, including OLMoE, Qwen3, and DeepSeek-style MoEs. Our pretraining experiments demonstrate that tying experts can reduce memory footprint by almost 2x at virtually no degradation in perplexity or downstream quality. By exploiting the parameter redundancy inherent in MoE pathways, our method provides a highly favorable compute-to-memory trade-off, advancing efficient training and scaling of next-generation LLMs.

Driven by their remarkable success in computer vision and inverse problem solving, score-based models are increasingly applied to wireless communications, where they show promise across a range of physical-layer tasks. However, despite this growing interest, the current literature often lacks a rigorous analysis of when score-matching offers a tangible advantage over traditional discriminative learning. This paper aims to address this gap through the use-case of channel estimation, a fundamental inverse problem in wireless systems. We present a theoretically grounded interpretation of score-based channel estimation through the lens of the perception-distortion tradeoff, identifying the conditions where score matching excels as well as its key limitations. In particular, by modeling downstream wireless tasks (e.g., capacity maximization) as functionals of the channel estimation process, we quantify the excess risk incurred by standard distortion-minimization approaches. Extensive numerical results show that under high predictive uncertainty, the large excess risk gap can be offset by score-based estimation, enabling near Bayesian-optimal precoding via the learned posterior, whereas in the low predictive uncertainty regime, discriminative distortion-minimization approaches are preferable due to lower complexity and more efficient use of model capacity.

Tool-augmented LLM agents rely on runtime filtering to decide which tools should be visible at each step. Causal Minimal Tool Filtering (CMTF) reduces tool-choice confusion by exposing only the next causally necessary tool frontier, but it assumes that the user request has already been mapped to a symbolic goal state. In practice, requests such as "handle my appointment" or "take care of this email" may correspond to multiple possible goals. This creates wrong-goal execution, where an agent follows a valid causal tool path for an unintended objective. We introduce GIST-CMTF, a goal-state inference layer that predicts candidate symbolic goals over the same state-transition vocabulary used by CMTF, estimates ambiguity, and either applies CMTF or exposes clarification as a causal action that produces missing goal or state variables. We evaluate GIST-CMTF across seven model backends, six filtering methods, and 120 controlled tool-use tasks. GIST-CMTF achieves 97.0% task success, compared with 80.1% for top-goal CMTF and 82.9% for semantic-goal CMTF. It reduces wrong-goal execution from 19.4% under top-goal CMTF to 2.5%, while preserving the one-tool exposure of causal filtering and using substantially fewer tokens than all-tools exposure. These results suggest that reliable tool-augmented agents should validate goal state, not only tool relevance, before exposing external actions.

For the development of Large language models (LLMs), recent approaches to generating pseudo intermediate reasoning have shown remarkable progress. But they typically rely on large numbers of correctly annotated answers to assess reasoning quality. This paper presents a semi-supervised framework that scales reasoning learning from minimal supervision, turning reasoning verification itself into a data creation mechanism. We train a lightweight reasoning-correctness classifier on only a few labeled samples, which judges whether intermediate reasoning traces generated by an LLM are valid. Furthermore, an entropy-based confidence threshold filters out unreliable samples, and the remaining high-confidence reasoning traces are used to fine-tune the model. Experiments on Verifiable Math Problems (Orca-Math subset) and Question Answering on Image Scene Graphs (GQA) with Visual Programming show that our method achieves accuracy comparable to using 10-15x more labeled data. Ablation analyses confirm that both the classifier and entropy filtering are essential for scalable and noise-resistant pseudo-labeling. By replacing expensive answer-level supervision with lightweight reasoning verification, our method provides a practical path toward constructing large-scale reasoning resources and paves the way for future autonomous reasoning systems that learn from minimal human input.

While Large Reasoning Models (LRMs) excel at complex tasks, they remain highly vulnerable to sophisticated jailbreaks and direct harmful queries. To address this vulnerability, prior works depend heavily on external manual data annotation for safety alignment. However, we observe that LRMs can inherently identify safety risks when being re-presented with original queries alongside their own reasoning trajectories – a capability we term Latent Safety Awareness. To leverage this safety awareness, we first employ Supervised Fine-Tuning (SFT) to explicitly induce safe tags to trigger safety analysis and guidance following the initial reasoning content for unsafe queries, while preserving standard responses for general queries to ensure adaptive triggering. Subsequently, we apply Direct Preference Optimization (DPO) to further enhance the correctness and stability of the safety analysis and guidance. Notably, responses required for both training stages are entirely generated by models being optimized. With (Safe Trigger) SFT and DPO, experimental results demonstrate significant safety enhancement. For example, the Attack Success Rate (ASR) of DeepSeek-R1-Distill-Llama-8B, on average, drops 24.65% and 36.72% on harmful and jailbreak benchmarks, respectively. Finally, our Safe Trigger method exerts almost no negative impact on general performance or user experience.

Current computer-use benchmarks primarily focus on software operation tasks in virtualized systems, whereas scientific instrumentation scenarios require coordinated control over complex interfaces, and feedback-driven parameter adjustment. However, directly evaluating agents on physical high-precision instruments is impractical due to high cost, safety risks, limited accessibility, and difficulty in ensuring reproducible evaluation. This motivates the need for a simulated yet realistic testbed that preserves the operational challenges of scientific instruments while enabling scalable and safe benchmarking. To this end, we introduce LabOSBench, a challenging benchmark for multimodal GUI agents built on a suite of web-based scientific-instrument simulators. Operating directly via a browser, LabOSBench avoids resource-heavy OS virtualization while supporting flexible task configuration and execution-based evaluation. Specifically, LabOSBench constructs 96 subtasks across eight instrument simulators, covering workflows from sample loading, alignment, parameter tuning, and data acquisition to result inspection. We evaluate general-purpose vision-language models, specialized GUI agent models, and advanced agentic frameworks at both subtask and end-to-end levels. Our experiments reveal that while existing agents can complete many structured GUI subtasks, they still struggle with feedback-driven operations and long-horizon workflow execution. Overall, LabOSBench provides a reproducible, low-cost testbed for advancing computer-using agents toward scientific-instrument control.

Existing vision-language model (VLM)-based AI-generated image quality assessment (AIGIQA) methods suffer from a fundamental semantic-distortion dimensional conflict: monolithic representations optimized for semantic discrimination inherently entangle compositional understanding with low-level perceptual sensitivity, rendering them blind to fine-grained quality degradations. We introduce MST-CLIPIQA, a multi-scale two-stream framework that achieves hierarchical vision-language alignment through explicit representational decoupling. Our architecture leverages dual CLIP encoders with complementary patch granularities: coarse-grained streams capture global semantic coherence while fine-grained streams preserve textural signatures and artifact patterns. An information bottleneck-inspired gated fusion mechanism performs adaptive cross-scale distillation, with optional cross-attention enabling prompt-anchored correspondence evaluation when generation prompts are available. Extensive experiments across five benchmarks establish new state-of-the-art results, achieving average improvements of 1.11 percent SRCC on quality and 2.35 percent SRCC on text-image correspondence prediction, while maintaining efficiency with only 0.8M trainable parameters. Our project is available at https://github.com/YMlinfeng/MST-CLIPIQA.

Conditional generative models are increasingly used as scenario generators for stochastic optimization, but standard training objectives emphasize uniform distributional fit rather than the downstream decisions induced by generated scenarios. This creates an objective mismatch: errors in statistically common regions may have little effect on decision regret, whereas errors in decision-sensitive regions can substantially change the optimal action. We propose Decision-Weighted Flow Matching (DW-FM), a regret-aligned training framework that preserves the simplicity of standard flow matching while reweighting its velocity-regression objective using decision-sensitive endpoint information. Theoretically, we connect downstream regret to pathwise velocity mismatch through a loss-induced decision discrepancy and an adjoint transport argument, yielding an ideal regret-aligned surrogate and practical endpoint-weighted objectives with regret guarantees. Empirically, we demonstrate the effectiveness of DW-FM on three CVaR-based contextual stochastic optimization benchmarks spanning synthetic portfolio, semi-real financial, and traffic-CVaR tasks, where DW-FM improves downstream regret over standard baselines.

Multimodal large language models (MLLMs) excel at visual reasoning but rely on text-based chain-of-thought (CoT), lacking interpretable visual intermediates. Existing methods use opaque tokens or external tools, missing key properties. We propose Gen-VCoT, a framework using expert vision models to generate RGB images as reasoning intermediates. It has three stages: visual grounding (SAM segmentation), geometric reasoning (Marigold depth maps), and semantic reasoning (Qwen2-VL integration). An adaptive router selects reasoning depth. Evaluations show Gen-VCoT improves spatial (25% better) and depth (50% better) questions, but may hurt simple factual queries. Text CoT outperforms visual intermediates on CLEVR (91.2% vs 62.5%), showing task-dependent optimal representations. Gen-VCoT establishes a new paradigm for interpretable multimodal reasoning.

Equipping Large Language Model (LLM) agents with effective skills is crucial for solving complex tasks in real-world systems like OpenClaw. In this work, we aim to develop a framework that automatically constructs such reusable skills to enhance LLMs in tool use, multi-step reasoning, and dynamic environment interaction. To this end, we propose Collective Skill Tree Search (CSTS), a novel tree-search-based skill construction framework that constructs structured, diverse and generalizable tree of skills. The core idea of CSTS is to leverage collective intelligence to jointly search, identify and compose effective skills via two iterative phases: Collective Skill Node Generation (CSN-Gen) and Collective Skill Node Assessment (CSN-Assess). CSN-Gen exploits collective knowledge from multiple models to explore diverse candidate skills for each subtask, enabling comprehensive skill exploration. CSN-Assess employs multiple models as judges to evaluate and select skill nodes with two scoring mechanisms: (1) collective quality scoring that aggregates independent evaluations to produce a robust estimate of skill effectiveness, and (2) collective transferability scoring that explicitly verifies whether a skill generalizes well across different models. With CSTS, we construct a set of comprehensive tree of skills along with skill-augmented training data, enabling models to effectively learn and utilize skills. Besides, we introduce Collective Skill Reinforcement Learning, which actively selects multiple relevant skills from the tree to broaden solution-space exploration, avoid being trapped by a single skill and its resulting homogeneous or suboptimal solutions. As a result, our trained model, OpenClaw-Skill, exhibits outstanding agentic capabilities in long-horizon planning, tool use and generalization over challenging benchmarks.

Agent skills are commonly distributed as SKILL.md files: human-readable procedural documents that describe workflows, tools, resources, and domain conventions. While convenient for inspection and reuse, this design requires the same reusable procedure to be repeatedly injected into the runtime context. We propose Skill-to-LoRA(S2L), a behavior-centric skill representation that replaces runtime skill text with skill-specific LoRA adapters. Rather than compressing the skill document itself, S2L models the behavioral change induced by the skill text: offline, the complete SKILL.md is used to synthesize skill-guided demonstrations; online, the full document is omitted and the corresponding LoRA adapter is dynamically loaded to activate the learned skill behavior. We evaluate S2L with Qwen3.6-27B on a 21-skill subset of SWE-Skills-Bench. Compared with the no-skill and Full Skill Text baselines, S2L improves pass rate by 2.9 and 5.2 percentage points, respectively, while reducing per-step token cost by 6.6% relative to Full Skill Text prompting. S2L matches or improves Full Skill Text on 18/21 skills and the no-skill baseline on 15/21 skills. Control experiments further show that the gains depend on skill-specific adapter alignment: Wrong-LoRA and Shared-LoRA both reduce performance. These results suggest that many procedural agent skills can be converted from runtime instructions into trainable, dynamically loadable behavioral modules. Code will be released upon acceptance.

As Large Language Models (LLMs) become embedded in everyday communication, capturing regional linguistic variation is essential for reliable and equitable language use. In Portuguese, European (pt-PT) and Brazilian (pt-BR) varieties remain unevenly represented, with pt-BR dominating in data quantity, while LLM preference for Portuguese variants remains underexplored. To address this gap, we introduce P3B3, an expert-curated language variety agnostic benchmark of conversational prompts, along with an evaluation framework for measuring variety bias and controllability. Experiments on several models show that most LLMs exhibit a strong bias toward pt-BR, with variation in controllability across models. These results highlight the need for more balanced multilingual representation across language varieties.

Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks. However, their safety remains a critical concern due to their susceptibility to adversarial prompt-based attacks. In this paper, we present UNIATTACK, an adversarial testing framework designed from a defense-oriented perspective to systematically construct effective black-box attack prompts. Unlike prior approaches that rely on static templates or iterative model-specific tuning, UNIATTACK extracts minimal but high-impact attack features from diverse existing attacks, optimizes them via a specialized attacker LLM, and composes them into flexible templates through automated refinement process. This feature-centric construction enables one-shot attacks that generalize across multiple models and safety categories, providing a practical tool for assessing LLM robustness. Our evaluation results shows that compared to the baselines, UNIATTACK achieves an average attack success rate (ASR) improvement of 64.63%-248.82% on models deployed with multi-layered defense mechanisms and it only takes 0.03%-4.96% cost of the baselines. UNIATTACK artifact is available at https://anonymous.4open.science/r/UniAttack-Artifact-30F1.

With the rapid advancement of video generation models, distinguishing between AI-generated and authentic videos has emerged as a challenging endeavor. The majority of existing research endeavors concentrate on the development of detectors for identifying samples generated by generative adversarial networks. Nevertheless, the detection of AI-generated videos, particularly those produced by text-to-video models, still remains an uncharted territory. Although state-of-the-art text-to-video models can generate realistic visual content similar to real videos, they fall short of generating the details of the images and the changes in details within the videos. Inspired by this, we address AI-generated video detection from a novel perspective of bit-planes, which can effectively describe the details or noises in images or videos. To this end, we propose a simple yet effective approach called Noise Amplification. This approach first extracts noise signals based on bit-planes, then amplifies these noise signals, and finally feeds them into the discriminator networks for video fake classification. Noise amplification is comprehensively constructed by incorporating three aspects: pixel-level intensity enhancement, region-level spatial amplification, and frame-level temporal aggregation. To evaluate methods of AI-generated video detection in challenging scenarios, we also introduce a benchmark named HardGVD. Extensive experiments on both the large-scale dataset GenVidBench and HardGVD show that our simple approach significantly outperforms state-of-the-art methods.

Policy gradient algorithms for language models optimize the same objective $J(\theta) = \mathbb{E}*{\tau \sim p*\theta(\tau)}[R(\tau)]$, which has exactly two factors: the trajectory probability $p_\theta(\tau)$ and the reward $R(\tau)$. Every method from REINFORCE to PPO to GRPO and their descendants modifies one or both factors to address a specific failure in the preceding formulation. Existing surveys organize these methods by domain or chronology, which obscures the rationale behind each design choice and the precise location of its intervention within the gradient estimator. This survey revisits the landscape of LLM policy optimization from $J(\theta)$ on first principles and uses the trajectory side, induced by $p_\theta(\tau)$, and the reward side, induced by $R(\tau)$, as the two axes along which methods are located. It covers the path from REINFORCE and PPO to GRPO, as well as post-GRPO variants, Agentic RL, and GRPO-OPD. The resulting framework is unified, diagnostic, and extensible: it analyzes methods from a shared objective, identifies which side each method modifies and why, and applies the same trajectory and reward axes across these settings. Across these settings, the framework also exposes compound failures that no single-side fix resolves and that therefore require joint design of the trajectory side and the reward side. The boundary cases and coupled failures identified by this map mark where existing solutions run out and provide a principled starting point for designing the next generation of LLM policy optimization algorithms.

Current multiparty turn-taking models often rely on complex microphone arrays or multi-camera setups, limiting their applicability in human-robot interaction scenarios. We introduce MuVAP, a causal multimodal framework that extends Voice Activity Projection by grounding acoustic predictions in face tracks, enabling speaker-aware turn-taking predictions from a monaural audio stream and a single camera view. To address the combinatorial complexity of modeling multiple speakers, we propose Role-Relative Projection, which maps any N-speaker interaction onto a fixed current versus next floor-holder state. Because existing audiovisual datasets contain disruptive editing cuts that break causal tracking, we introduce the Audio-Visual Conversation Corpus, a 31-hour dataset of unedited, single-camera multiparty conversations. Evaluations demonstrate that MuVAP outperforms strong baselines on Shift-Hold and next-speaker prediction tasks across two- and three-speaker settings.

We re-interpret Transformer pretraining as a fast-slow, singularly perturbed flow along depth, with untied weights as its non-autonomous feature. The linearised dynamics is a depth-ordered product of layer maps. Along a token-homogeneous reference trajectory, the linearised layer factorises along the eigenbasis of a frozen attention kernel. Past a computable saturation depth, the flow factors through the block coarse-graining – in other words, running the layers is running the coarse variable, dually. Weight perturbations supported on the decaying bundle move neither the persistent component of the distinguished trajectory nor the frozen kernel to first order, so the framework partitions parameter space into visible and invisible directions, with the cross-block coupling of the slow path sitting entirely on the visible side. How large a gate the slow path can carry is bounded by a stability margin. On the data side: if block emissions follow an exponential family, block-mean pooling captures all the information the slow path can use; but if neighbouring blocks carry no shared structure, no cross-block channel can help the prediction, and the gate amplitude is invisible in the prediction risk. Stability delimits what the architecture may do; the data decides what it will.

Large language model (LLM) agents increasingly take actions (screening applicants, recommending credit, triaging patients), yet fairness for LLMs is still measured by grading answers. We introduce AgentFairBench, a cheap, reproducible, multi-domain benchmark for demographic disparity in the actions of LLM agents. Grounded in a companion framework, the Bias Conduction Framework (BCF, restated here), it spans three regulator-anchored domains: hiring, lending, and medical triage. Synthetic, demographic-neutral profiles are evaluated in counterfactual matched sets that vary only a name-coded race x gender signal (in the Bertrand Mullainathan tradition), under four agent scaffolds of increasing agency (direct, chain-of-thought, multi-agent deliberation, tool-augmented). A NumPy-only harness computes counterfactual flip rate, mean absolute score difference (MASD), action-rate disparity, and tool-invocation disparity, with bootstrap confidence intervals, paired tests, and false-discovery-rate control, for single-digit dollars per model. A live leaderboard with a held-out private split and a contamination canary admits external models by submission. Our pilot (864 decisions plus a test-retest replication) carries a methodological lesson: comparing a six-group score spread against a two-run noise difference overstates disparity by ~ 2.4X through statistic arity alone. Against an arity matched noise floor and an omnibus group test, claude haiku 4 5 shows no demographic effect above sampling noise (0 of 120 pairwise and 0 of 9 omnibus contrasts survive correction); a planted-bias test confirms the instrument detects disparity when present. The contribution is a sound, sensitive, adoption-ready instrument, the arity matched null methodology, and open artifacts to scale it. Code, data, and harness are released under open licenses, with an anonymized review artifact.

Medical diagnosis and treatment are dynamic processes in which patient states evolve over time and clinical interventions alter future outcomes. Although current medical AI can detect disease, estimate risk and generate reports, many systems still return static labels or scores, offering limited insight into how illness may progress or how alternative interventions may reshape its trajectory. Medical world models adapt the world-model idea from artificial intelligence to healthcare by learning internal simulators of patient-state dynamics. Their long-term goal is to help clinicians anticipate deterioration, compare treatment-conditioned futures and tailor care to individual patients. Yet relevant work remains scattered across foundation models, longitudinal modelling, disease simulation, treatment-effect estimation, reinforcement learning and digital twins. To bridge this gap, this review outlines a roadmap for advancing medical AI from isolated diagnosis and prediction toward medical world models that simulate disease evolution and support intervention decisions. This roadmap is organized around three coupled capabilities: patient-state construction, clinical dynamics modelling and intervention decision support. Across representative systems, the comparison highlights what each capability contributes and how partial components can be integrated into more mature perception–dynamics–planning systems. Finally, we identify the challenges involved in turning plausible rollouts into clinically useful simulators. Related literature is available at https://github.com/1999kevin/awesome_medical_world_models.

A personalized AI agent needs a user memory: a persistent model of who the user is, built across many conversations and consulted on each new one. Today this memory is almost always stored as unstructured text, a knowledge graph, or a flat store of facts, and consulted by retrieval – fetching the entries most similar to the current request. Such "bag-of-facts" memory recalls individual facts well, but because storing a fact and acting on it are separate steps, it struggles to resolve contradictions, aggregate over many records, or enforce rules. We argue that user memory should instead be executable. We introduce User as Code (UaC), a paradigm in which an agent's model of a user is a living software project: typed Python objects hold the user's state and ordinary Python functions encode the rules that govern it, so representing and reasoning about the user happen in one medium an interpreter can run. The enabling mechanism is a two-phase pipeline: an append-only log that never discards a fact, periodically checkpointed into typed code. This changes what memory can do. On standard long-term conversation benchmarks, UaC matches both a full-context upper bound and the strongest prior memory systems on recall (78.8% on LOCOMO). Its advantage emerges where representation matters most. On aggregate questions over a user's history – "how many international trips did I take last year?" – retrieval-based memory collapses (6-43%) while UaC stays near-perfect (99%), because the answer is a one-line computation over typed state rather than a search over text. And because its rules execute deterministically whenever the state changes, UaC can surface unsolicited, safety-critical alerts – such as a newly prescribed drug that conflicts with an allergy recorded months earlier – a capability query-driven memory cannot provide.

Transformers perform computations through many successive attention and feedforward blocks, allowing them to learn complex correlations between a large collection of coupled variables. When does stacking successive attention-feedforward computations over many layers provide a computational advantage over a single transformer block? We address this question by examining in-context learning in generalized linear attention transformers. We first introduce a general theory of distributed inference in such transformers, subject to constraints on communication and depth. We show that such systems can exploit internal representations (`function vectors') to infer a latent context variable at increasingly finer scales over its layers. For an in-context linear regression task, the theory predicts that while one-layer transformers without feedforward blocks are optimal for Gaussian priors over the context variable, multi-layer transformers are superior for non-Gaussian, tree-like priors. Trained linear attention transformers reproduce quantitative predictions from the theory. Using causal key-patching experiments, we verify that function vectors in intermediate layers mediate adaptive routing of information. Our results suggest that depth and feedforward blocks enable transformers to implement adaptive inference, and this is advantageous when the distribution over latent variables has hierarchical structure.

Learning-based manipulation policies have made substantial progress in real-world robot manipulation, particularly for short-horizon action generation. However, deployment in open workspaces remains fragile under unexpected local scene dynamics, such as moving objects, transient occlusions, or disturbances near the intended motion. Existing runtime monitors often rely on global observation anomalies, policy uncertainty, or frame-level visual changes, and struggle to distinguish task-relevant execution risk from benign visual variation. We introduce PATCH, an action-chunk-conditioned latent patch innovation monitor for deployment-time intervention. Given the active action chunk, PATCH defines a projected execution corridor, predicts latent patch evolution inside it, and accumulates persistent residuals unexplained by the robot's own motion. These residuals form a localized intervention signal that allows PATCH-Router to pause execution, select an available recovery source, and resume the original policy once localized innovation subsides. Experiments on real robot rollout data show that PATCH produces more stable and context-relevant triggers than competing runtime monitors. Real-robot deployment further demonstrates monitor-driven intervention and policy resumption for disturbance-aware manipulation. Project Page: https://yananzhou5555.github.io/PATCH/.

Modeling dimensional affect in longitudinal text requires distinguishing current affect estimation from future affective change forecasting. Existing approaches often treat each text as an independent observation and apply similar assumptions to both tasks, without testing whether they rely on different information sources. This paper investigates that distinction using longitudinal self-reported ecological essays and feeling-word entries. We propose the Trait–State Affective Prediction (TSAP) framework and its temporal extension E-TSAP for per-text valence and arousal prediction, evaluated on a held-out prediction test set of 1,737 entries from 91 users. We further propose the Affective Change Forecaster Hybrid (ACF-Hybrid) for next-step affective change forecasting, evaluated on a held-out forecasting test set of 46 users. For prediction, E-TSAP achieves composite Pearson correlations of 0.670 for valence and 0.449 for arousal. For forecasting, textual representations perform worse than compact numeric trajectory baselines: the text-inclusive model achieves only r=0.316 for valence and r=0.284 for arousal, whereas a simple prior-state baseline reaches r=0.615 and r=0.670, respectively. ACF-Hybrid, using dimension-specific numeric trajectory features, achieves r=0.659 for valence and $r=0.658$ for arousal. These results show that textual semantics support current affect prediction, whereas future affective change is better captured through prior numeric trajectory dynamics.

Temporary accommodation has become a major fiscal and administrative pressure for English local authorities, particularly in London, where demand and costs have risen sharply. This paper documents the creation and use of DOMUS, a cloud-based, AI-enabled decision-support system built from scratch at the University of East London and customised for the needs of London Borough of Newham to support statutory Temporary accommodation placement. DOMUS integrates household case records, policy-constrained affordability and suitability rules, and live private-rental listings within a single governance-aligned workflow. The system combines transparent, rule-based filtering with large language model-assisted search to standardise the application of bedroom need, affordability thresholds, geographic preferences, and accessibility requirements, while preserving officer discretion and audibility. Household and property attributes are encoded into policy-consistent representations prior to AI-assisted ranking and explanation. A pilot deployment in Newham's secure environment evaluated operational performance relative to manual workflows. Results indicate substantial reductions in search time, improved adherence to key placement constraints, and high staff satisfaction, while maintaining statutory compliance and role-based accountability. Beyond TA, the paper frames DOMUS as replicable digital public infrastructure: a modular, cloud-native Software-as-a-Service architecture that can be deployed across other UK boroughs and adapted to other public administration tasks characterised by scarcity, rule-bound eligibility, and high stakes. The findings demonstrate the feasibility of scalable, ethically governed AI deployment in local government and contribute to debates on AI-enabled public value creation in e-governance.