Papers

Ultrasound is widely used, but acquisition quality is heavily dependent on the operator's knowledge and expertise. With demand for examinations outpacing the supply of trained sonographers, operator-guidance systems aim to close this gap by instructing a less trained user how to move the probe toward a target view. In this paper, we propose a retrieval-induced latent transition model for ultrasound acquisition dynamics, formulating ultrasound operator guidance as multi-step planning and retrieval in a world model. Using a V-JEPA 2.1 backbone, observations are first encoded into a latent space where anatomically related views lie close together. We then retrieve similar views from a reference database containing encoded latent states and corresponding probe positions and orientations. Rather than learning a parametric transition function, we directly use physically executed transitions from the database to establish our nonparametric, retrieval-induced transition model that supports receding-horizon planning. At deployment, guidance is generated from the live ultrasound image feed alone, without any probe tracking hardware. Applied to carotid ultrasound, the proposed planner reaches the target view in 86% of retrospective closed-loop episodes, versus 52% and 43% for representative baselines, outperforming both on every target view, including the challenging longitudinal internal and external carotid artery views. A prospective feasibility study on unseen volunteers, run in real time on a CPU using distillation, reaches 83% target-view reachability. Because planning is driven by proximity to any encodable goal latent, the same world model can navigate back to any previously acquired, patient-specific frame, supporting reproducible longitudinal imaging for e.g. perioperative or follow-up monitoring.

We study contextual queueing bandits, where a learner schedules jobs while learning unknown service rates modeled by logistic functions of job-server features. Performance is measured by queue length regret, the expected excess queue length at round $t$ relative to an oracle that knows the service rates. Existing decaying-regret guarantees either have a suboptimal decay rate or require a known fixed horizon. They also assume context-wise slack and a strictly positive minimum eigenvalue of the feature covariance. In this paper, we propose WISE (Widest Interval Selection with Elimination), achieving rate-optimal $\widetilde{\mathcal O}(t^{-1/2})$ queue length regret at every sufficiently large time without knowing the horizon. We assume capacity slack, meaning that expected incoming workload under best-server service is below service capacity, and impose no covariance lower bound. Our analysis uses a workload potential measuring the expected service attempts needed by waiting jobs on their best servers. Its drift on nonempty rounds combines a negative term ensured by capacity slack with errors from suboptimal service choices. Then an elliptical potential count bounds how often WISE selects wide confidence intervals, thereby limiting the number of rounds with large service errors. We also sharpen the arrival-rate dependence of an existing lower bound and make its dependence on feature dimension and server count explicit. We prove another lower bound that quantifies the increase in regret as the normalized capacity slack decreases; to our knowledge, this is the first such lower bound for CQB. Simulations show small regret even when context-wise slack fails.

Small independent (indie) game startups face fierce competition when developing games with limited time, budget, and resources. Continuously testing and experimenting with new ideas, features, and content is essential to validate and guide development toward a viable and successful game. Such continuous experimentation (CE) requires access to users and user data, which is often very limited in the early stages of development, both in general and, in particular for indie game companies. We provide insights and recommendations on how to perform experimentation and game testing in pre-release stages of indie game development based on an exploratory interview survey with 10 independent game developers from different companies. We provide a framework for CE that highlights key parts to consider when planning and implementing an experiment. Current practices for experimentation within indie game development are also described for the early development stages of ideation, preproduction, feature production, and content production. Our empirical findings offer insights and recommendations into how to conduct experiments during pre-release stages of game development, specifically for Indie game companies. Other software startups, particularly those with a value proposition centred around interactive and satisfying user experiences, can also benefit from our research.

Formally reasoning about Rust programs requires a rigorous formal semantics, especially in the context of deductive verification and concurrent programming. We present a modular, flexible semantics for a significant subset of (close to) source code level Rust, based on the recent locally abstract, globally concrete semantics framework, separating local evaluation of expressions from their composition into concrete traces. The semantics is extended to model Rust's asynchronous programming features and Rust's most popular async runtime, Tokio. Based on our more abstract formalization, we establish the fairness of Tokio's scheduler. Further, we show the applicability of our semantics to deductive verification of Rust by providing soundness proofs for a Rust program logic.

Diffusion models provide expressive priors over trajectories, but adapting these priors to test-time constraints requires maintaining feasibility and consistency across successive control decisions. We introduce Persistent Particle Planning (P3), a sequential Monte Carlo framework for diffusion control that maintains a weighted population of candidate plans across replanning steps. At each control step, P3 shifts and partially re-noises the candidate trajectories, refines them under the latest observation, and uses constraint-aware weighting and resampling to select among alternative continuations without retraining the diffusion model. We consider denoising and replanning as one Feynman–Kac particle system and analyze it under an idealized repair. We prove that the re-noising depth controls how reliably a kept plan stays on its route, and that keeping a rare, well-separated route takes far fewer plans than rediscovering it by sampling from scratch. Experiments under multiple test-time constraint configurations show that population reuse reduces route switching and improves success without constraint violations. Because P3 refines earlier plans instead of redrawing them, it also needs fewer denoising iterations per replan. On maze-navigation tasks, it plans faster than both regenerated populations and methods that correct a single sampled plan by constrained optimization. Code and pretrained models are available at https://github.com/p3-username/p3-anon.

AI agents built on large language models (LLMs) run shell commands, read and write files, and reach the network, typically with their user's privileges. However, what an agent does during an execution is difficult to understand: tests assert on the result, and the agent's trajectory records only what the agent reports about itself, which may omit behavior executed by its subprocesses. We present AgentSpy, an approach that observes an agent from outside the agent. AgentSpy runs the agent in an isolated environment, configured by a declarative specification, and records the system calls and network traffic of the agent and of every process it executes. Based on this monitoring, AgentSpy supports two families of analyses: conformance analyses, which measure obligations, i.e., what an agent execution should do, and safety analyses, which check prohibitions, i.e., what an agent execution must never do. We instantiate one analysis of each family. The reliability analysis uses rules to summarize each run by the environment resources the agent uses: the commands it executed, the files it accessed, and the hosts it contacted. The security analysis applies deterministic rules to the system calls of an execution. For reliability, we evaluated AgentSpy on 77 tasks with the codex harness and three recent LLMs, executing each task three times. Sets of repeated runs of the same task are more similar than sets that include runs of another task in 92.2% of the comparisons. Among tasks for which all three runs pass outcome-based tests, the agent performs task-unrelated activities in 18% of the cases, reads the grading files in 7%, and does not use the developers' guidance in 17%. For security, the generic rules of AgentSpy detect four of five attack categories we considered, with no false positives across 50 runs.

While AArch64 CPUs are becoming strong market contenders, their software ecosystem lags behind the mature x86-64 environment, hindering the adoption of the new architectures and impacting user experience. Binary translation bridges this divide by converting binary code from one architecture (e.g., x86-64) to run on another (e.g., AArch64), allowing legacy software to benefit from modern hardware's performance and energy efficiency advantages. Current translation methods are typically either dynamic, which adds significant runtime overhead, or static, which struggles with reliability due to the inherent complexities of binary analysis. This paper introduces a new static, assembly-to-assembly translation paradigm that transforms binary code ahead of execution, generating portable, efficient native-like binaries that run on AArch64 devices without runtime frameworks. Benefiting from recent breakthroughs in large language models (LLMs), we provide a practical and automated translation engine that produces high-quality code with minimal human intervention. To ensure correctness, we introduce a crucial verification step, where we split the assembly code into simplified snippets, enabling efficient and scalable semantic verification. Our evaluation shows that this approach significantly outperforms existing open-source solutions with a large margin, producing binaries with near-native performance. Furthermore, it shows substantial improvements over the leading industrial translator, ExaGear, illuminating a promising new direction for cross-architecture binary translation research.

Molecular dynamics simulations proceed by integrating the Langevin equations over many small femtosecond timesteps. This poses a challenge for estimating ensemble properties and transition dynamics that occur on much longer timescales. We introduce Langevin Flow Maps, which extend machine-learned force-fields to additionally learn the stochastic Langevin integrator. We show that Langevin Flow Maps enable large-timestep molecular dynamics and recover accurate dynamical properties of the system, while running an order of magnitude faster than current machine-learned force fields. Further, by training on a diverse molecular dataset, we demonstrate a path towards transferable Langevin Flow Maps.

Early development unfolds in caregiver-infant dyads, where infants' sensorimotor streams are shaped by physical contact and face-to-face interaction. Yet developmental robotics simulators commonly model infants in isolation, limiting the study of caregiver-mediated experience. We present a caregiver-enabled extension of the Multi-Modal Infant Model (MIMo) in MuJoCo that turns MIMo into a controllable platform for replaying dyadic interaction and generating dense infant-perspective observations. The system provides (i) an articulated caregiver model compatible with MIMo morphologies, parameterized from anthropometrics and optionally resized to a recorded caregiver; (ii) a workflow to replay naturalistic caregiver-infant holding and soothing interactions; and (iii) logging and visualizing the infant's first-person multimodal experience (we show touch and vision). We showcase the tool on touch by introducing origin-aware contact logging that disambiguates self-, caregiver-, and environment-generated contact and supports aggregation into touch-rate statistics comparable to manual coding. While we showcase tactile analysis, the platform is intended more broadly as a generator of multimodal dyadic datasets (touch and egocentric vision) for modeling the development of social interaction.

Latent world models based on Joint-Embedding Predictive Architecture (JEPA) are deterministic by design. While successful in fully observable scenarios, this paradigm breaks down when past observations and actions lead to multiple plausible future possibilities, e.g., due to occlusion. We introduce EpicWorldModel, a framework to train stochastic JEPAs for environments and tasks with inherent uncertainty under partially observability. We jointly train the EpicWorldModel predictor with its latent representation space to directly predict multiple potential future states using a flow-matching objective, when the goal-relevant scene content is absent from the conditioning history. We show that flow predictive variance, motivated by its relation to an upper bound on predictive entropy, serves as a useful exploration guidance for planning. By incorporating this uncertainty signal into Cross-Entropy Method (CEM)-based planning, our approach balances goal-reaching with exploration of uncertain regions where occluded goals are most likely to be located. We demonstrate the effectiveness of EpicWorldModel through a series of latent planning experiments with the best or on-par performance across tasks, showing up to 22% empirical improvement in success rate over LeWorldModel.

Vision-language-action (VLA) models currently demonstrate strong performance in a wide range of real-world robotics tasks. However, they often still lack the generalization ability to handle large visual out-of-distribution shifts. Post-training of VLAs with reinforcement learning (RL) has been shown to benefit robustness, but significant room for improvement remains. In this work, we systematically study the effect of image augmentation on VLA post-training. We find that it is crucial to augment only the critic module during RL updates, while leaving the actor's input clean during both rollouts and updates. For $\pi_{0.5}$ and GR00T N1.5 this raises out-of-distribution success on LIBERO-Plus by $7.8$ and $10.0$ points respectively, while augmenting the actor collapses training entirely. We investigate a range of augmentation types and strengths, and provide practical recommendations for improving generalization in VLA post-training.

Composed image retrieval (CIR) aims to retrieve a desired target image from a query consisting of a reference image and a modification text. This task exhibits an unusual representational asymmetry: the modification text specifies a transition from the reference state, whereas retrieval candidates depict completed target states. This creates a representation mismatch for zero-shot methods that query pretrained vision-language spaces directly with transformation-oriented language. We study this mismatch and reformulate zero-shot composed image retrieval as target-state reconstruction followed by retrieval. We instantiate this formulation with ASAP-CIR, a training-free framework that reconstructs a static target representation using a frozen multimodal large language model (MLLM). The representation combines multiple holistic descriptions with a variable set of importance-weighted atomic semantics, thereby preserving both overall target identity and fine-grained visual constraints. Retrieval then integrates holistic state alignment, atomic constraint grounding, and calibrated target-state evidence aggregation. A controlled text-only diagnostic shows that target-side static query formulations achieve more reliable retrieval than dynamic composed query formulations, particularly when source-state semantics must be suppressed or transformed. Experiments on FashionIQ, CIRR, and CIRCO further characterize the effectiveness and limitations of this representation principle, with the clearest gains on the multi-target CIRCO benchmark. These results show that how composed intent is represented before retrieval is a consequential design choice, distinct from the choice of retrieval backbone itself.

Trust is crucial in the digital world, particularly in the age of systems based on artificial intelligence. Traditionally, system correctness is demonstrated by proving that the system satisfies the required properties. However, digital systems involve humans, who can make mistakes, break rules, or even intentionally cheat the system. Technical devices may also malfunction or cause errors. Therefore, external stakeholders need to trust a system throughout its operation. To address this challenge, we propose the concept of continuous trust. In this paper, we present a detailed explanation of this concept, based on a running example of a business's refund department. The paper concludes with a discussion of related work, such as compliance checking and certification, as well as an outlook on further questions regarding the formalization and the necessary tool support.

Large-language-model release pipelines increasingly combine commitments, signatures, provenance records, and heterogeneous verification backends. Yet validating every submitted object does not establish that a release realizes every requirement of its registered transformation. An untrusted realization proposer may omit a required relation, propose an unauthorized evidence-sharing assignment, or bind valid evidence to the wrong object. This verification-boundary failure is termed Semantic Omission under Valid Evidence (SOVE). Hybrid Cryptographic Relation-based Semantic Plan Verification (H-CRSPV) is a replicated admission layer that enforces required-set completeness before release consumption. Before evidence selection, an authorized registration entity commits an authenticated authority record. Validators independently derive the required-obligation multiset, check exact entry-occurrence coverage, validate proposal-induced evidence sharing, and bind admissible groups one-to-one to keeper-resolved objects. Evidence remains provisional until the challenge window closes and an atomic finalizer activates the release. The analysis establishes structural exactness and conditional semantic guarantees under explicit assumptions. Across 36 omission artifacts, submitted-object validation accepts all 36 because every submitted object passes its backend-specific verifier. H-CRSPV rejects all 36 while accepting all six honest releases. The prototype also validates six restricted source-to-RelationIR bindings and rejects all 60 tested mutations. In a continuous four-validator Qwen2.5-1.5B workflow, the same authority record remains fixed across three legal releases with different post-registration availability states. These results show that per-object validity does not establish complete, correctly bound, and finalized release evidence.

Computational pathology has the potential to improve clinical outcomes through a demonstrated increase in diagnostic and prognostic accuracy. However, the development and validation of deep learning algorithms still require annotated data, a costly procedure involving expert pathologists who already face critical workforce shortages. Existing coreset selection methods to optimize annotation efforts currently all rely on hyperparameters tuned on natural-image benchmarks that do not transfer to histopathology and are cumbersome to use in clinical practice. In this study, we present GCcore, a novel label-free coreset selection method that embeds every image of a dataset with any pathology foundation model and greedily selects the samples that collectively maximize the global coverage of the embedding space. The proposed method provides a lower-bound guarantee on the global coverage of the returned coreset for any coreset size, while being completely hyperparameter-free and deterministic. We demonstrate GCcore's superior performance over 14 baselines including state-of-the-art methods across 10 tasks and datasets spanning whole slide image classification, tile classification, and tissue segmentation, where it ranks first on six and within the top three on nine, while also demonstrating how existing methods can shift by up to five rank positions depending on their hyperparameter settings. Code is publicly available at https://github.com/OncoAI-ULBHUB/GCcore.

With the rapid development of artificial intelligence, the emergence of various Large Language Models (LLMs) has created a rich model ecosystem. However, this also brings a key challenge: how to select the optimal model for a specific user query. LLM routing addresses this need by dynamically assigning queries to the most suitable expert in the pool of candidate models. However, existing routing frameworks often simplify this process to a standard classification task; thus, a critical vulnerability is exposed when multiple candidate models correctly answer the same query. We formalize this capability overlap as routing noise, which misleads the router with arbitrarily correct candidate models, ultimately leading to routing collapse (a severe decline in generalization ability on unseen tasks). To address this problem, we propose a novel Cluster-Aware Soft-Labeling Routing (CASLR) framework. CASLR shifts the evaluation paradigm from the success of a single query to macro-domain consensus by replacing traditional one-hot vectors with a masked softmax mechanism. Specifically, for experts who answer incorrectly, we penalize their target probability to zero; for the remaining candidates, we directly compute continuous fine-grained soft labels based on their global clustering utility scores. We then use these refined soft labels to supervise a lightweight router. Specifically, the framework not only demonstrates superior accuracy on multiple benchmarks, but also outperforms Llama-3.3-70B-Instruct by 7.80% in overall average performance. Furthermore, the extremely low routing inference latency of only 1.13s further confirms that CASLR can achieve efficient system scheduling with almost zero additional overhead, while ensuring high response quality.

A prior longitudinal study of silent failures in a production LLM agent runtime (arXiv:2606.14589) found that about 70% were discovered by a human looking at the product as a user while thousands of tests and governance checks stayed green, and posed mechanizing part of what the human eye does as an open problem. This paper reports our attempt. We built an automated user-viewpoint observer targeting the most dangerous class, fail-plausible failure, in which an internal error becomes fluent, plausible output to the user. It is a two-layer pipeline: five deterministic signals distilled from incident postmortems escalate to an LLM judge whose verdicts must cite verbatim evidence or be discarded. Ground truth is 24 labeled production postmortems with explicit honesty boundaries: 16 of 24 are structurally invisible to any content-reading observer, and we say so. Offline, the deterministic layer achieves 6/6 regression detection with 0/4 false positives, each detector proven load-bearing by sabotage; held-out recall on novel patterns is 0/4. It is, so far, a regression engine. Deployment followed pre-registration: shadow mode caught and retired one systematic false positive on its first run, the 26-day shadow window then ran clean, flip criteria were fixed before the shadow data was read, and the analysis protocol was frozen before the enforcing-mode window opened. That window (12 observed days) fired zero verdicts; per the pre-registered path we report live precision as undefined rather than narrating quiet as success. The observer also produced ten silent failures of its own, confirming that the judge inherits the taxonomy it judges. We release the corpus, detector, and scorecard as a runnable bench: mechanization today retires the human's regression scanning so the eye can specialize in novelty; prediction remains open but is now measurable under frozen rules.

Tokenizer-free language models remove the inductive bias of fixed tokenizers by modeling text directly as bytes, but the resulting longer sequences substantially increase computation and eliminate explicit text abstractions. We ask whether this additional computation can be useful, and whether standard Transformers can learn the abstractions that tokenization provides. We study these questions on Transformers without specialized tokenization-related architectures. With token-superposition training and hash embeddings, byte Transformers consistently outperform subword Transformers as model size scales. We further find that byte Transformers build local text abstractions as external tokenizers: a set of segmentation-like positions are used to collect local context representations, and restricting up to $25\%$ of intermediate layers to these local representations preserves downstream performance. Finally, these learned structures induce highly non-uniform generation difficulty, with uncertainty concentrated near local structure boundaries; exploiting them for speculative decoding yields $3.4\times$ more accepted tokens than in subword Transformers.

Serving a large language model (LLM) across a fleet of deployments requires several weight-precision operating points. Multi-precision formats serve them all from one stream whose prefixes are valid lower-precision codes, instead of storing multiple copies. We present StagQ, a multi-precision weight format whose main stream is a 2-bit group-wise affine base followed by a configurable number of 1-bit refinement planes on a dyadic step schedule. Every supported precision is a readable prefix, decoded by an affine map derived from metadata shared across all precisions, with no per-weight lookup. A sparse side record, filled both before and after the grid is fitted, holds out the few weights the grid serves worst. We report two configurations of the encoder. At two bits the cheaper one leads the strongest multi-precision baseline on Llama-3.1-8B, Phi-4, and OLMo-2-7B by 3.1 to 7.0 MMLU points, at a slightly lower logical rate. At three bits it leads on Llama-3.1-8B, leads on Phi-4 at a higher rate, and ties on OLMo-2-7B. At four bits it ties on all three, at a higher rate. In a batch-one matrix-vector product on an NVIDIA A100 GPU, timed on synthetic weights, our kernel is faster than the two baseline kernels in most shape-precision cases.

Verifier-guided decoding can prevent harmful reasoning steps from contaminating subsequent generation, but typically relies on an external learned verifier. We ask whether a language model can instead reject its own bad reasoning steps. We define a prefix's recoverability as the probability that the frozen generator can complete it correctly. Diagnostics show that adjacent recoverability changes are often difficult to resolve with practical Monte Carlo budgets, while same-prefix candidates exhibit a sparse low-recoverability tail. We introduce Self-Step Rejection (SSR), which trains a lightweight LoRA acceptance gate on the generator backbone while keeping the base model frozen. SSR uses confidence-qualified first-passage supervision: steps before the first resolved crossing of a root-relative recoverability barrier are accepted, the crossing step is rejected, and unresolved steps and suffixes are excluded. Training combines pointwise classification, same-prefix pairwise learning, and group-relative policy refinement using final-answer correctness. At inference, SSR accepts candidates or resamples from the unchanged prefix under rejection budgets, without an external learned verifier. Across three reasoning models and five mathematical reasoning benchmarks, SSR improves macro-average accuracy over single-pass decoding by 5.4–10.1 points using 1.21–1.40x as many generated tokens, and achieves the highest macro-average accuracy among evaluated step-level methods. Full-solution scaling methods require 4.47–8.27x the single-pass token cost for comparable performance.

The goal of this article is to study optimal high-order Taylor-based polynomial quasi-Trefftz spaces for first-order time-harmonic Maxwell's equations. Compared with standard polynomial spaces, the purpose of quasi-Trefftz spaces is to retain the same high-order best approximation property but more efficiently: their dimension is considerably smaller. To achieve this goal, they approximate only smooth solutions to the governing equation rather than to approximate general smooth functions. While there is a natural definition of Taylor-based polynomial quasi-Trefftz spaces for scalar equations, the situation is fundamentally different for vector-valued equations, as the naive quasi-Trefftz property does not systematically define the smallest space with the desired best approximation property. This article identifies the optimal quasi-Trefftz spaces for first-order time-harmonic Maxwell's equations, proposes two approaches to construct quasi-Trefftz bases, and proves the spaces' best approximation property. The theoretical results, which strongly leverage polynomial Helmholtz decompositions and the exactness of the polynomial de Rham sequences, are validated with numerical experiments.

Reinforcement learning can substantially improve a reasoning teacher, but it is unclear which of those improvements survive when the teacher supervises a smaller on-policy student. We study this question in mathematical reasoning by comparing teacher lineages before and after GRPO, multiple student scales, direct GRPO, and several on-policy distillation objectives. The central finding is that transfer is structured rather than scalar: teacher strength alone does not make dense distillation competitive, while an RL-improved teacher creates useful but metric-dependent student gains. This motivates Transfer-Stratified On-Policy Distillation (TS-OPD), which screens training problems by the joint sampled success of the student and teacher, routes acquisition problems to gated forward KL, routes consolidation problems to gated reverse KL, and adds an entropy brake to protect sampled coverage. Across the main comparison, TS-OPD is the strongest student objective for macro average correctness with the GRPO-improved teacher, while pass@K remains more mixed. Ablations show that the gains come from routing and token gating rather than skipping problems. These results support a transfer-aware view of OPD: stronger teachers help when the supervision direction and token budget match the student's observed ability, not merely because the teacher endpoint is stronger.

Robot delivery studies can overstate transport capacity when travel to pickups and human support fall outside the modeled schedule. We formulate a location aware dispatch model that couples robot admission to transporter support and shared elevators, charging, and cleaning. The model replays 33,079 observed hospital requests; missing contents, deadlines, staffing, and completion times remain explicit scenario assumptions. Two full grids compare human dispatch, a resource aware controller, and a proximity and workload benchmark in 30 paired replications per scenario. An exploratory extension tests a simpler deadline admission rule under the same operating model. Pickup travel increases demand on a pooled elevator bank. In one high staffing case, raising assumed elevator capacity from two to four reduces human only lateness from 55.11% to 3.18%, exceeding the dispatch differences. Direct policy comparisons and robot coverage distinguish admission selectivity from system service. The analysis explains why a robot can pass a deadline admission test yet delay service through staff handoffs and shared facilities. Its contribution is a reproducible evaluation of coupled dispatch workflows, with a clear separation between admission, completion, and return to availability. The results are conditional comparisons, not estimates of hospital benefit or released clinical capacity.

Diffusion policies provide expressive action distributions for continuous-control reinforcement learning. However, safety-aware online diffusion policy optimization remains underexplored, particularly methods that use predictive reachability information without an explicit dynamics model. We propose Reachability-Aware Diffusion Policy Optimization (RADPO), a model-free method that combines predictive first-hit safety estimation with cumulative-cost budget feedback. RADPO learns a discounted first-hit reachability value that captures the discounted risk of a cost event, assigns larger weight to events that occur sooner, and uses this signal to shape the reward. A separate dual-like multiplier adjusts the shaping strength according to realized episodic costs relative to a prescribed budget. The diffusion actor improves through weighted denoising regression on candidate actions scored by the reward critic. Our approach requires neither a learned dynamics model, action gradients through the critics, nor differentiation through the reverse diffusion sampler. We establish theoretical properties of the reachability value and show that accumulated reachability penalty provides a conservative surrogate for future discounted cumulative cost. Across ten continuous-control safety tasks, RADPO achieves competitive reward-cost trade-offs, with substantial reductions in constraint violations on several tasks relative to the compared baselines. Our theoretical and empirical analysis supports that combining reachability with cumulative budget feedback is a viable approach to safety-aware diffusion policies.

We study last-iterate convergence in unknown two-player zero-sum discounted Markov games with bandit feedback. The players learn independently along a single trajectory without observing each other's actions. We develop Adaptive Regularized TD Learning (ARTD), which achieves a $\widetilde{\mathcal{O}}(t^{-1/4})$ duality gap bound for the current policies under a uniform hitting time assumption, with high probability simultaneously over all rounds and starting states. This improves the $\widetilde{\mathcal{O}}(t^{-1/(9+\nu)})$ rate of Cai et al. (2023), for any fixed $\nu>0$, under the same feedback model and hitting time assumption. Our algorithm requires no knowledge of the hitting time bound, the time horizon, or the confidence level. To stabilize policy learning as value estimates change, we separate fast temporal difference averaging from bounded value updates. We adapt log-barrier regularization to the progress of value estimation, controlling both policy and value errors throughout learning. Together, these mechanisms enable fast convergence of the policies actually played, even when the players learn independently from bandit feedback.

Image compression, restoration, and generation all require a way to measure how different two images look to a person. Pixel error ignores how people see, while the most accurate perceptual distances are typically fitted to human judgments, tying them to a fixed data and resolution. For example, when image resolution is doubled, the correlation of DISTS with human scores on TID2013 drops from 0.815 to 0.717. We introduce the Jacobian Lens Distance (JLD), which derives its perceptual geometry from a frozen vision encoder rather than from human labels. JLD combines the locality of early patch features with the perceptual sensitivity captured by later encoder representations. Specifically, we use the encoder Jacobian to identify directions in the early feature space that most strongly affect the encoder output, producing a fixed metric tensor, $E[J^\top J]$, which we call the Jacobian lens. The lens is fitted only once from 100 unlabeled images, taking about 35 seconds. Locally, this construction defines a pullback metric in pixel space, giving JLD a clear geometric interpretation that can be directly analyzed on real images. Across four standard perceptual databases, JLD achieves state-of-the-art performance and consistently outperforms LPIPS, DISTS, PieAPP, and DreamSim. JLD is also robust to changes in image resolution, on TID2013, its lens-term correlation remains nearly unchanged when the resolution is doubled, decreasing only from 0.850 to 0.845. We further introduce JLD-fast, which is $4\times$ faster than LPIPS-VGG while achieving a mean correlation of 0.911. Finally, JLD naturally extends to video, reaching a correlation of 0.786 on Waterloo IVC 4K compared with 0.611 for VMAF.

Domain adaptation aims to turn a general-purpose large language model (LLM) into an expert for a target domain. While the dominant SFT+RL pipeline offers a convenient cold start, it may reduce exploration diversity and introduces additional complexity through multi-stage optimization. These limitations motivate RL-only adaptation. However, pure on-policy RL suffers from a cold-start problem, while mixed-policy RL still falls short: informative tokens in teacher outputs are learned too slowly in early training, and stale teacher outputs can hinder later improvement. We identify these two failure modes as Gradient Starvation and Teacher-Distribution Anchoring. To address them, we propose One-stage Policy Optimization (OnePO), which treats teacher outputs as transient guidance for policy improvement. OnePO combines Adaptive Objective Evolution to strengthen learning on informative low-probability teacher tokens and Teacher Retirement to discard teacher outputs once the current policy can surpass them. On medical adaptation, OnePO achieves 67.2 on HealthBench (Total) with only 20K training samples, outperforming SFT+RL and pure RL by 2.7 and 7.4 points, respectively. We further scale OnePO to produce HuatuoGPT-3, an open-source medical LLM series whose 27B variant reaches 70.1 on HealthBench (Total) and 71.4 on HealthBench Professional, surpassing frontier models such as GPT-6 Astra. Models and code are available at https://github.com/FreedomIntelligence/HuatuoGPT-3.

Natural face-to-face human–robot interaction requires a robot to understand an evolving social situation, decide when to engage, and express its intent through coordinated physical behavior. Yet existing approaches rarely close this loop: foundation-model agents provide increasingly capable multimodal reasoning and memory but remain largely disembodied, while expressive virtual agents do not face the physical constraints of real robots, and physical social robots typically address social reasoning and embodied expression only partially. We present ARISE, a unified framework that bridges Agentic Reasoning and Interactive Social Embodiment on the Sophia humanoid robot. ARISE integrates multimodal context understanding, long-term memory, and reactive and proactive interaction to determine when and what to communicate, and translates social intent into robot-native gestures coordinated with speech and mechanical facial expressions through streaming execution. Extensive evaluations on Sophia demonstrate strong perceived interaction quality, expressive and well-coordinated embodied behavior, and substantial latency reductions through streaming execution. These results highlight the importance of jointly reasoning about what to communicate, when to engage, and how to physically express social intent for natural interaction with humanoid robots. Project Page: https://robosocial.github.io/

Smart ports increasingly depend on IoT-enabled digitalization to turn heterogeneous operational processes into measurable, optimizable workflows. Accordingly, this paper first provides a concise review of IoT-enabler technologies for port digital transformation, emphasizing how sensing, connectivity, and data integration capabilities support real-time decision-making in port environments. Motivated by the growing emphasis on operational decarbonization reflected in the European Green Deal and the Sustainable Development Goals (SDGs), we then present a data-driven fleet scheduling framework for landside port operations at the Port of HaminaKotka (Mussalo terminal), Finland. The scheduling framework reallocates vehicle operating hours to minimize total CO2eq emissions while preserving the same aggregate workload. The study uses a two-year dataset from 77 port-operating vehicles, analyzed at monthly and annual aggregation levels, to derive vehicle-specific intensity metrics (CO2eq per operating hour) and identify reallocation opportunities. We formulate the scheduling task as a linear programming workload allocation problem that minimizes the weighted sum of assigned hours while keeping total required hours fixed, enforcing fleet-level caps on CO2eq and energy use, and respecting per-vehicle operating limits. The optimization is solved using the HiGHS linear programming solver via SciPy's linprog. Results show that shifting utilization away from high-intensity vehicles and toward more efficient units yields substantial system-level improvements with no reduction in total operating hours: the optimized schedule achieves an approximately 31% reduction in total CO2eq and a simultaneous 9.4% reduction in total energy consumption.

Valuing player actions in football requires accounting for strategic interactions among 22 players, including off-ball movements and defensive positioning. Existing reinforcement-learning-based methods commonly aggregate decisions at the team level or estimate player values independently, leaving strategic interdependence among players insufficiently represented. This study proposes an action valuation framework inspired by Markov perfect equilibrium (MPE) for all players. Each possession is modeled as a finite-horizon dynamic game, with each player represented as an autonomous agent whose policy depends on the current game state. MPE is used as a motivating solution concept rather than an exact equilibrium. To improve interpretability, we use Expandable Decision-Making States (EDMS) and decompose the Q-value into a successor-feature basis and a linear reward-weight vector. The value basis is estimated by linear TD initialization followed by nonlinear refinement. Using tracking and event data from 95 J1 League matches, we compare the proposed formulation with an independent reinforcement learning baseline. Because the two formulations define TD errors in different target spaces, TD MSE is used only for within-formulation consistency. With EDMS fixed, the independent baseline assigns the highest value to forward movement in 99.21% of evaluated off-ball states, whereas the most frequent direction under the proposed formulation accounts for 17.63%. Team-level average Q-values show a negative association with season-level expected goals for the baseline and a weakly positive association for the proposed formulation. Qualitative analyses illustrate context-dependent valuations of off-ball movements and defensive positioning. Overall, the proposed formulation produces more context-sensitive action rankings, although the comparison does not isolate the MPE-inspired component.