Science & Mathematics

Text-to-image (T2I) platforms typically return several images per prompt so users can explore different visual interpretations and choose one that matches their intent. However, T2I models are usually optimized for single-image quality which comes at a cost of multi-image diversity, limiting this exploration. Diversity is also contextual: one user wants variations in background, while another wants them in artistic style, and the same user may later want variations in clothing. The generated images should differ along whatever axis the user cares about. In this paper, we introduce T-DIG, a text-conditioned diversity framework for image generation and editing. T-DIG is an iterative framework comprising multiple modules that lets users type prompts, inspect default generations, request variations using natural language, and continue refining outputs until they're satisfied. At its core, T-DIG uses an LLM policy that produces K axis-conditioned prompts or edit instructions for a frozen generator or editor. We train this policy with GRPO using a text-conditioned diversity reward and alignment penalties. Because the image generator remains frozen, T-DIG applies to open-weight, distilled, and proprietary models. We also release the first dataset for text-conditioned prompt diversity in image generation, with the training and validation splits built from human-written axes and a test set drawn from real user interactions with T-DIG. T-DIG far exceeds baselines in improving text-conditioned diversity, while preserving base-prompt alignment across a variety of metrics and human judgements. We show that user-directed diversity exploration can be added to a wide range of image generation models, open and closed, without the need to access their weights. Website: https://image-study.org/t-dig/

A central obstacle to self-improving agents is the absence of a reliable fitness signal for realistic stateful tasks. We introduce \textsc{VeriEvolve}, an evaluator-first evolution framework that constructs this missing evaluation layer before optimizing the agent. From task instruction, VeriEvolve synthesizes instruction-grounded challenge states and an executable evaluator that checks them. During each round of workflow evolution, the evaluator is frozen and serves as the fitness signal. Between rounds, VeriEvolve revises the evaluator by converting the end states of strong and weak runs into a pair of counterfactual test cases. Across all 30 MCPMark Filesystem tasks, VeriEvolve constructs 30 evaluators with 141 challenge states, achieving 141/141 agreement on the generated suites and 113/122 agreement on held-out states produced by executor agents. Evaluator-guided evolution increases externally verified success from 6/30 to 18/30 for GLM-5.2 and from 27/30 to 30/30 for Claude; refinement removes all three false positives that the weak executor exposes. Cross-environment studies on PostgreSQL, Playwright, Notion, and GitHub further expose complementary limits from observability, state representation, and search/execution capacity. These results show that executable evaluators can be synthesized and used to guide search when task success is observable and an external verifier is available for calibration.

We study a jump-modified Wasserstein gradient flow of the squared maximum mean discrepancy generated by the energy kernels $K(z)=-|z|^q$, $0

In recent years, automated fruit classification systems have become a more critical component in precision agriculture for efficient yield estimation, quality control, and supply chain optimization. However, they still face significant challenges under varying quality, fruit maturity, illumination, texture degradation, morphological attributes, domain shift, and post-harvest handling conditions. In this study, we address the challenging issue of cross-grade banana variety classification. This is a real-world setting where models that have been trained on specific quality grades must generalize to unseen grades to handle significant domain shift. Under a rigorous Leave-One-Grade-Out evaluation protocol, we present a thorough comparative analysis of CNNs, ViTs, and dual-stream hybrid architectures using a large-scale dataset of 31,678 banana images with three varieties and three quality grades. Specifically, to address the drawbacks of single-paradigm frameworks, we present a dual-stream Swin ResNet hybrid framework enhanced with KL-divergence-based self-distillation to align probabilistic feature representations across the CNN and Transformer streams. Comprehensive experimental analyzes show that the presented hybrid framework with KL-divergence based self-distillation achieves better overall performance, i.e., it attains a mean accuracy of 81.25% and significantly surpasses CNN and Transformer baseline models. Qualitative analysis further confirms that the hybrid framework in this study improves discriminative feature transferability, improves attention localization, and stabilizes optimization.

We present a local and sparse kernel method for learning the solution operators of incompressible flows. It builds on our earlier property-preserving kernel method, whose global output reconstruction and dense operator regression scale poorly. Our method replaces the global output reconstruction by local divergence-free interpolants with divergence-free polynomials of any degree, solved in parallel on the GPU. These interpolants are divergence free, periodic on periodic domains, and, with a multiscale kernel, approach Kolmogorov statistics under refinement. A compactly supported kernel, positive semidefinite in any input dimension, makes the operator regression sparse. Its support radius, and hence the sparsity, is fitted to data, and optional affine polynomials in the input capture global trends. Operator Lagrange weights join the two. They cost one sparse solve per new input and act on the training fields before the output reconstruction, so their local coefficients are never formed. We show that, unlike direct evaluation, Lagrange evaluation does not amplify solve errors by the cancellation among spatial coefficients. On ten fluid benchmarks, validation selects sparse matrices nearly everywhere, with densities that mostly decrease as the training set grows, and affine augmentation lowers the error by more than an order of magnitude for forced isotropic turbulence. These sparse models are at least as accurate as our earlier dense method and more accurate than neural operators. Lagrange evaluation is as accurate as direct evaluation with local output reconstructions, and up to nearly three orders of magnitude more accurate with global ones. We also present GPU timings and storage.

Radiation treatment planning requires balancing competing objectives to satisfy clinical criteria while accommodating physicians' preferences. This study aims to develop an evidence-driven, multi-agent compound AI system that integrates DRL-based automated treatment planning with LLM-based conversational plan refinement for proton PBS therapy. A policy network trained using PPO first generates multiple plans without human intervention, from which one is selected as the target plan and the others serve as references for subsequent refinements. For challenging cases requiring further adjustments, an LLM-based multi-agent system enables plan refinement through natural language interactions. The system comprises a planning agent that recommends evidence-supported adjustments, a chatbot providing a unified conversational interface, and an evaluation agent that retrieves clinical metrics and identifies constraint violations. To enhance domain-specific reasoning, the planning agent based on Qwen3-14B is designed to justify its recommendations using evidence from previously generated plans and post-trained on task-specific data using SFT and GRPO. The framework was trained and evaluated using 21 patients with H&N cancers, with 5 PPO-generated plans per patient. Of these, 50 plans were selected for instruction-guided refinement. Compared with the base LLM, the post-trained Qwen3-14B demonstrated improved instruction-following, information retrieval and domain-specific reasoning capabilities. The resulting adjustments more effectively improved user-prioritized objectives while limiting deterioration in competing objectives, yielding more clinically appropriate trade-offs in patient-specific plan refinement. The proposed compound AI system provides a user-friendly planning platform, offering a promising approach to personalized proton PBS treatment planning.

Speculative decoding accelerates large language models by verifying drafted tokens in parallel. New draft-training objectives are usually credited with the acceptance they add over cross-entropy on externally written responses, yet many pipelines let the target rewrite them. We ask how much of that gain survives. With a vision-language target and a block drafter, we train three objectives on four versions of one corpus: cross-entropy on corpus tokens, token-level distillation from the target, and distillation gated to positions that would survive verification. Distillation and the gate add large gains on external responses, but after greedy regeneration, distillation adds a smaller gain and the gate little or none. The shrinkage persists across data orders, position weights, verifiers, decoding temperatures and, for distillation, initializations and learning rates. Most of it remains at matched supervised length and at each objective's best measured training length. A second vision corpus shows the shrinkage, as does a text-only replication, for distillation also with an autoregressive drafter. Objective gains should therefore be measured against a target-regenerated baseline and across training lengths. Our code is available at https://github.com/js-lee-AI/TargetRegeneration.

Coding agents are rapidly advancing from single-file generation to long-horizon repository-scale engineering, yet the evaluation of their capabilities to author interactive extended reality (XR) applications remains an open challenge. Unlike traditional software, XR applications operate within dynamic 3D physical environments where runtime robustness depends jointly on continuous user motion, spatial input, and environmental sensing. We introduce GenXR-Bench, the first benchmark for the end-to-end evaluation of coding agents in XR software development. GenXR-Bench contains 112 expert-authored tasks spanning 24 feature implementations, 21 bug repairs, and 67 application generation tasks. Held-out tests combine scripted and adaptive interactions with programmatic and visual assertions to evaluate core functionality and runtime behavior. GenXR-Bench's testing suite achieves 96.5% accuracy against blinded expert judgments of 124 candidate applications executed on consumer XR hardware. Evaluating 10 models on GenXR-Bench, we find that the strongest configuration achieves only 50.9% overall Pass@1. Failure analysis identifies recurring misunderstandings in asynchronous sensor lifecycles, physical grounding, and embodied interaction semantics. GenXR-Bench establishes a reproducible testbed for evaluating coding agents in the interactive and physically situated conditions of spatial computing.

The modeling of the behavior of agents in strategic environments and the prediction of the resulting outcomes has long been a challenging problem; this has been the focus of game theory. The introduction of AI agents as human-aids or as sole decision-makers expands the underlying question: Can we model behavior and predict outcomes of strategic games that involve a mix of AI agents and human players? As an initial answer, we propose Correlated Quantal Response Equilibrium (CQRE) that combines and generalizes classical solution concepts such as Quantal Response Equilibrium and Correlated Equilibrium. We answer questions of existence and propose a method for computing the CQRE that is a best fit to a given joint action distribution. We demonstrate the empirical effectiveness of CQRE predictions using a diverse collection of complex general-sum games, including high-rank and large-action two-player games, challenging multiplayer games, and a large-scale extension of the Selten--Chmura setting to AI--AI and human--AI play.

Large language model (LLM) agents are often improved by iterating until a fixed verifier is done. Once that verifier saturates, the loop has nothing left to climb. We instead score agents against the current population, and a frozen panel records whether anyone got better. The panel mean can rise inside the seeds by elimination alone. We therefore count a run as training only when its final mean beats the best generation-zero member. A merge is admitted only when the child moves toward the donor, past the child the same operator produces at zero dose, and the lower confidence bound on that movement reaches half the requested dose. That is the admission test. A detectable shortfall rejects the operator, and the test is otherwise undetermined. We keep realised fitness φas the selector and reference performance θas the unused ruler. Every measurement uses gemini-3.1-flash-lite on one negotiation task, and no fixed-oracle arm was run. In the open loop, tactic append grafts short donor rules and is admitted. Free rewrite moves only a third of the requested dose and is rejected. Template append pastes raw donor replies into the child. Its movement clears the bound on the first probe but not on the re-probe, and it is left undetermined. A held-out re-probe on the five situations the merge never saw confirms that both appends move, and it does not rescue free rewrite. Neither append rises with the dose. Constrained rewrite is admitted in the open loop and was not run in the closed loop, which changes only the operator. The population, the scores and the task stay fixed. No free-rewrite run beats the best generation-zero member. Every tactic-append run and every template-append run does. Sampled loop children keep that split. Free rewrite moves no further toward the donor, and both appends still clear the bound, by less than in the open loop.

Reinforcement learning for stochastic systems typically optimizes expected cumulative rewards, while reliable and repeatable behavior also depends on how the state distribution evolves over time. Optimizing expected return alone does not guarantee that this distribution converges to a desired target or remains stable. This paper develops a theoretical framework for learning policies that stabilize state distributions. We formulate the problem as a Dissimilarity-based Markov Decision Process (DMDP), in which the policy acts on the current state distribution and the objective measures its dissimilarity to a target distribution. We establish sufficient conditions under which the optimal policy makes the target distribution asymptotically stable. To support policy learning, we introduce a finite-dimensional representation of distributions and show how stability guarantees for its parameter dynamics extend to the underlying state distributions. We further develop certificates for the learned policies, including their deployment using estimated distribution parameters. These results quantify how learning and estimation errors affect the guarantees and identify conditions under which learned policies retain asymptotic stability. For practical implementation, we combine distribution estimates and target-dependent rewards with PPO and SAC. A computable example on a linear system illustrates the proposed theoretical certificates. Furthermore, experiments on a HalfCheetah task demonstrate the benefits of distribution feedback and explicit target matching for regulating the velocity distribution.

Estimating food mass from a photograph is central to image-based dietary assessment, but whether trained models transfer to new cameras and foods is unclear. We fine-tuned DINOv2-base on 2,253 weighed Nutrition5k dishes to predict mass from one RGB photograph and compared it with a zero-shot vision-language model, Qwen3-VL-32B, on Nutrition5k and three external datasets: ASA24 studio portions, ECUSTFD whole foods and Food Portion Benchmark meal trays. In domain, the fine-tuned model's mean absolute error was 24.8 g, less than half of Qwen's. On external datasets it did not beat Qwen. For a food it had never seen, it ranked portions by size, but no better than a count of food pixels. Its gram scale was wrong in two ways: it changed with how much of the scene the photograph showed, and it was off by a different factor for each food. Training on other foods or trays from the tested dataset cut the external error by 38 to 65%. DINOv2-large, a larger backbone trained on the same dishes, did not reduce the external error. One labeled photograph of the same food cut the model's ASA24 error to 28.3 g, better than that photograph achieved alone. Prediction intervals that held the true mass for 90% of Nutrition5k dishes held it for at most half of external photographs. Nutrition5k often photographed the same plate several times, so a random test split shared near-identical photographs with training and overstated accuracy. Single-image mass estimators therefore need labeled photographs from the setting where they are used.

This research-creation artistic report presents Resonance and Depth, a 9-minute immersive electroacoustic/acousmatic performance that treats timbre and space as primary compositional materials. Built from live electronic percussion and a personal corpus recorded, curated, and composed by the author, the work investigates how timbral identity and musical form can emerge through real-time recombination, spatialisation, and performer-system interaction rather than conventional harmonic development. The performance is realised as an artist-in-the-loop co-creative multi-agent system integrating MACAT, MACataRT, a MIDI-based musical agent, a spatialisation layer, and a conductor agent. These components recombine and transform the performer's material through concatenative synthesis, audio mosaicing, symbolic mediation, physically inspired synthesis, and object-based spatialisation. The work approaches spatialisation as an active compositional process in which position, trajectory, depth, diffusion, width, and apparent size participate in musical phrasing and form. Through this practice-based framework, Resonance and Depth examines how performer identity can be retained, transformed, and redistributed across human, algorithmic, timbral, and spatial processes within an immersive co-creative performance ecology.

Assembly language models (ALMs) are becoming important for automated binary analysis, yet their token-level interfaces often obscure numeric-like operands. In two corpora, such operands account for 45.7% and 40.9% of operand occurrences and may denote branch targets, global data, stack slots, constants, or unresolved pointer-derived values. Existing normalization strategies often lose their identities and structural relationships. We present NumAnchor, an input-boundary adapter that represents recoverable numeric-like operands as typed, canonicalized program entities. NumAnchor encodes code, data, and stack context in compact structural side descriptors, preserving entity identity and locality without increasing the host sequence length. These descriptors are fused into input embeddings before the first Transformer layer, while the host architecture, pretraining objectives, and downstream protocols remain unchanged. Probing frozen instruction-level embeddings yields 98.7% hierarchical-location accuracy and AUROC scores of 0.932 and 0.907 for jump and call target alignment, respectively, showing that the encoded structural information remains recoverable. Across multiple ALM families, NumAnchor achieves relative improvements of up to 35.0% in Recall@1 and 31.7% in MRR on 10k-candidate function retrieval, and improves execution-aware type recovery by up to 5.2 F1 points. Ablations show complementary gains from code, data, and stack descriptors with modest overhead.

Verifier stacks increasingly sit inside post-training and test-time compute loops. We study a specific control loop: a component verifier is evaluated on fresh policy outputs against the full success label and refreshed when that aggregate score falls. For a conjunctive target $y = F \wedge M$, its on-policy AUC is $(1-q)A_{\mathrm{own}} + qA_{\mathrm{cross}}$, where $q = \Pr[F=1 \mid y=0]$. As the policy masters $F$, $q$ can rise toward one, removing weight from $F$-failures and rewarding information about $M$. We call this on-policy audit collapse. We derive a sharp identified set, a complete-erasure threshold, and the exact point at which the audit can prefer a worse component verifier; its population optimum is the full-outcome predictor, not the component oracle. An exact oracle exhibits the collapse, a natural multi-label text control shows inversion can select a head with lower canonical $F$-AUC at the observed failure mixture, and a prediction-registered ECG study shows that acting on the audit can reduce off-policy $F$-AUC, transfer the damage to an unseen generator, and increase downstream constraint violations. Preserving own-failure support prevents the damage. Matching label-complexity bounds and a controlled-mixture audit give the corresponding repair: audit the component on its own failures, and keep those failures in the refresh distribution.