Humans, animals, and modern machine learning models exhibit impressive abilities to learn complex behaviors and generalize these behaviors to unseen situations. This ability requires us to learn rules and regularities that allow for such generalizations. At the same time, in most complex environments, any rule will have its exceptions. How do learning systems balance between learning general regularities and memorizing exceptions? We argue that a lack of task paradigms has hindered the study of this essential ability. To address this gap, we introduce a novel task, transitive inference with exceptions, that tests for relational generalization and memorization of an exception to the relational rule. We then analytically characterize the behavior of a simple, theoretically tractable model of neural network learning (kernel ridge regression) across a broad family of representations and task parameters. We find that these models can balance between relational generalization and memorization, but unlike for transitive inference without an exception, successful generalization is sensitive to the specific representational geometry. We explain why this task is more challenging mechanistically by drawing on our analytical theory. Finally, we validate our theoretical insights in pretrained language models that are finetuned on ordered relations, finding that these models successfully generalize according to the transitive rule, but also make the kinds of systematic mistakes predicted by our theory. Overall, our theory shows how learning systems can balance between relational generalization and memorization, explains how this can go wrong, and emphasizes the need for new task paradigms designed to probe this ability.

Employees often struggle to identify ``who knows what,'' leading to organizational productivity losses. We investigate whether Large Language Models (LLMs) can infer individual domain knowledge directly from long-term Slack logs. Analyzing 27,188 messages from 43 users, we evaluated seven models (including Gemini, Claude, and GPT families) by comparing their zero-shot estimates against self-reported skill ratings from 27 participants. Gemini 2.5 Flash achieved the lowest error (MAE 21.13%), while GPT models showed significantly larger discrepancies. Notably, estimation accuracy depended only weakly on message volume, indicating that more text alone does not guarantee better inference. These findings demonstrate the feasibility and current limits of automated expertise mapping, highlighting the need for privacy-preserving deployments and richer, structure-aware representations of human knowledge.

As state-of-the-art neural networks are deployed on reasoning and algorithmic tasks, exactness guarantees become increasingly important. However, high average-case accuracy can still mask inconsistent behaviors. This motivates exact certification, which asks for the smallest set of labeled examples needed to certify that a learned hypothesis equals the target. We show that while some hypotheses are easy to certify, even minimal overparametrization can make certification exponentially hard across several hypothesis classes. For threshold circuits of depth $\ge 2$, adding a single extra gate can force certificate sizes exponential in the input dimension. We show an analogous hardness result for log-precision Transformers with only constant architectural overhead. We also characterize approximate certification, showing that allowing only polynomially many mistakes still requires exponentially large certificates, whereas constant relative-error guarantees can hide exponentially many mistakes. Empirically, we study certification for constructed circuits and trained Transformers for recognizing binary addition. While the constructed circuits instantiate the exponential barrier for certification, the trained Transformer analysis shows that imperfect models can evade detection by large uniformly sampled certificate candidates.

Large Language Models (LLMs) are optimized to produce distributionally plausible continuations rather than to explicitly verify whether generated propositions are entailed by source documents. This inductive bias enables generalization, but it does not encode whether responses are grounded with respect to a reference. These issues limit the use of LLMs in domains where strict factual correctness is crucial, such as clinical decision support. Existing hallucination detection approaches improve factuality through retrieval augmentation, self-consistency, or claim verification, but generally do not learn directly over alignment topology. To leverage alignment topology as an inductive bias, we construct aligned bipartite graphs between reference information and LLM outputs and train a graph neural network (GNN) to model alignment structure using message passing. The method achieves state-of-the-art results on four diverse hallucination and question-answering datasets, outperforming all compared methods, including foundational LLMs such as GPT-4o.

Video recordings of child-caregiver interactions enable investigation of attentional dynamics during naturalistic behavior. Such multimodal recording also allows researchers to examine how attention interacts with action and language use in real time. However, manual annotation of such data is time-consuming. Here, we introduce GazeBehavior Annotation Toolkit, a deep-learning-based toolkit designed to facilitate three key processes in data preprocessing and feature extraction: post-hoc synchronization across multiple videos, semi-automatic annotation of gaze target categories, and categorization of participants' poses and hand actions. This toolkit improves the efficiency and scalability of feature extraction from human egocentric eye-tracking and video data. Such improvement is critical in supporting large-scale and longitudinal investigations of attentional dynamics and naturalistic behavior in human early development.

While multi-task learning based automatic radiology report generation (RRG) is widely adopted to ensure clinical consistency, most focus on architectural designs yet remain limited to coarse linear scalarization strategies. These strategies cannot effectively balance the hard constraints of discriminative clinical supervision with the smoothness requirements of report generation. To address these problems, we analyze the failure mechanism of linear scalarization from the perspective of gradient dynamics, utilizing the stochastic differential equation (SDE) framework to characterize it as a "Double Dilemma" of drift term deviation and diffusion term decay. Based on this, we propose a backbone-agnostic optimizer named Conflict-Averse Magnitude-Enhanced Gradient Descent (CAME-Grad). Through conflict-averse direction rectification and magnitude-enhanced energy injection, the algorithm not only ensures geometric validity, but also avoids local optimal solutions. Then, the adaptive gradient fusion mechanism is used to establish a dynamic balance between the theoretical optimal direction and the task-specific inductive bias. Experiments show that as a universal plug-and-play optimizer, CAME-Grad brings substantial and consistent improvements across eight diverse RRG methods, elevating overall clinical efficacy performance by an average of 2.3% on MIMIC-CXR and 1.9% on IU X-Ray. Our code is available at https://github.com/vpsg-research/CAME-Grad.

Motion degradation, manifested as blur in global shutter (GS) images or rolling shutter (RS) distortion in RS counterparts, remains a fundamental challenge in computational imaging, especially under fast motion or low-light conditions. While prior works have treated blur decomposition and RS temporal super-resolution as separate tasks, this separation fails to exploit their intrinsic complementarity. In this paper, we propose a unified framework to invert motion degradation and reenact imaging moment by jointly leveraging the complementary characteristics of GS blur and RS distortion. To this end, we introduce a novel dual-shutter setup that captures synchronized blur-RS image pairs and demonstrate that this combination effectively resolves temporal and spatial ambiguities inherent in both modalities. For allowing flexible performance-cost trade-offs, we further extend this dual-shutter setup to a stereo Blur-RS configuration with a narrow baseline. In addition, we construct a triaxial imaging system to collect a real-world dataset with aligned GS-RS pairs and ground-truth high-speed frames, enabling robust training and evaluation beyond synthetic data. Our proposed network explicitly disentangles motion into context-aware and temporally-sensitive representations via a dual-stream motion interpretation module, followed by a self-prompted frame reconstruction stage. Extensive experiments validate the superiority and generalizability of our approach, establishing a new paradigm for realistic high-speed video reconstruction under complex motion degradations. Codes and more resources are available at https://jixiang2016.github.io/dualBR_site/.

Safety classifiers are essential safeguards within generative AI systems, filtering harmful content or identifying at-risk users when interacting with large language models. Despite their necessity, these models are trained on sensitive datasets including discussions of self-harm and mental health, raising important, yet poorly understood, privacy concerns. Membership inference attacks (MIAs) allow adversaries to infer membership of examples used to train models. In this work, we hypothesize that identifying the examples on which the classifier is least confident are informative for an adversary to infer membership. This reflects a localized failure of generalization, where the model relies on memorization to resolve ambiguity in the training set. To investigate this, we introduce a new boundary-targeted selection strategy that identifies low confidence examples that amplify the signal of an examples membership within a training set. Our experimental results show that an adversary can recover 19% of the conversations a safety classifier flagged as indicating user distress, at a 5% false-positive rate, on a classifier fine-tuned for detecting a user who may require emotional support. This is $3.5$ times more than attacking using state-of-the-art MIA methods alone. Finally, we characterize the boundary laying examples and show that content-based filtering is ineffective for protection, and existing noise strategies can effectively mitigate susceptibility of these examples.

Ensembles of neural networks typically outperform individual networks but incur large computational costs, whereas weight aggregation produces less costly, yet also less accurate, aggregate models. We introduce partial fusion of networks, which interpolates between ensembles and weight aggregation and thus allows for a flexible tradeoff between computational cost and performance. A direct way to achieve this is to extend existing weight aggregation methods based on neuron-level similarity between different networks, where partial fusion then only aggregates weights of neurons which are most similar. We showcase one particular method to jointly identify which neurons are most similar and match them via partial optimal transport. Further, we consider the more general perspective of weight aggregation and partial fusion as generalized pruning of ensemble models, where neurons cannot just be deleted, but also linearly combined. Finally, we show that generalized pruning applied to a single network yields similar benefits as partial fusion by allowing for a tradeoff between isolating, deleting, and linearly combining neurons based on similarity. Our code is available at https://github.com/Fabian-Mor/partial_fusion_nn.

Whole-body Humanoid-Object Interaction (HOI) is bottlenecked by the scarcity of high-fidelity 3D data. While video generative priors offer a promising alternative, existing methods suffer from \textit{Representation Misalignment} due to their reliance on geometric priors (e.g., explicit CAD models), and \textit{Retargeting Complexity} arising from intensive morphing and morphological mismatch. We propose Imagine2Real, a zero-shot HOI framework for flexible, geometry-free interaction. To resolve misalignment, we formulate robot and object motions as unified 4D point trajectories. To overcome retargeting complexity, our Keypoints Tracker tracks only sparse critical points (base, hands, and object), entirely bypassing the error-amplifying retargeting process. To maintain natural gaits despite these sparse signals, we utilize the latent space of a Behavior Foundation Model (BFM) as the tracker's search domain. Using a progressive training strategy, Imagine2Real learns robust behaviors with simple tracking rewards, enabling zero-shot physical deployment within a motion capture(mocap) system.

This report presents our solution for the WeatherProof Dataset Challenge, namely CVPR 2026 8th UG2+ Challenge Track 2: Semantic Segmentation in Adverse Weather. For the semantic segmentation task under adverse weather conditions, we propose a semi-supervised segmentation pipeline. Our method is trained exclusively on the WeatherProof dataset, without using any additional external data. Specifically, we adopt UniMatch V2 as the baseline model and treat all degraded-weather images as unlabeled data for semi-supervised training, thereby fully exploiting the data distribution provided by the challenge. During inference, we further apply test-time augmentation to improve the robustness and segmentation accuracy of the final predictions. The code is publicly available at: https://github.com/ylb888/weatherproof-challenge-unimatchv2.

Feed-forward 3D Gaussian Splatting models offer fast single-pass reconstruction,but scaling them to match per-scene optimization quality is fundamentally hindered by the scarcity of large-scale 3D annotations. A practical compromise is predict-then-refine,where post-prediction optimization compensates for the limited capacity of the feed-forward network. However,standard feed-forward 3DGS is trained solely for zero-step rendering error,ignoring whether its output constitutes a good initialization for the downstream optimizer. We present ForeSplat,an optimization-aware training framework that equips feed-forward 3DGS models to produce initializations explicitly designed for rapid,effective refinement. By offloading part of the scene-modeling burden to the optimizer,ForeSplat substantially reduces the capacity pressure on the feed-forward model,making high-quality reconstruction feasible even with compact networks. At its core is MetaGrad,a lightweight multi-anchor meta-gradient training rule that bypasses costly higher-order differentiation through the 3DGS optimizer. MetaGrad unrolls a short inner-loop refinement trajectory,samples anchor states,and back-propagates aggregated first-order gradients to the prediction head as a surrogate optimization-aware signal. This fine-tuning adds no inference cost and enables high-quality reconstruction within seconds after a few refinement steps. We instantiate ForeSplat on diverse backbones,including AnySplat,Pi3X,and a distilled variant tailored for edge deployment. Across all tested architectures,a ForeSplat-trained initialization converges in fewer refinement steps and reaches a higher peak reconstruction quality than its vanilla counterpart,even fully converged. The framework consistently bridges the gap between amortized prediction and per-scene optimization,establishing a practical path toward lightweight,high-fidelity 3D reconstruction.

Computed tomography (CT) is a central to three-dimensional medical imaging, yet CT-based artificial intelligence remains fragmented across task-specific models for segmentation, classification, registration, and report analysis. Here we present FlexiCT, a family of CT foundation models trained by agglomerative continual pretraining on 266,227 CT volumes from 56 publicly available datasets, forming a large-scale public resource for CT representation learning. FlexiCT uses agglomerative pretraining across three stages: two-dimensional axial pretraining, three-dimensional anatomical pretraining and report-guided semantic alignment. This training strategy supports slice-level, volume-level and vision-language analysis. Across five downstream task families (segmentation, classification, registration, vision-language understanding and clinical retrieval), FlexiCT matches or exceeds prior task-specific approaches on multiple benchmarks. Its embeddings further organize CT scans along gradients associated with various tumor stages, suggesting that CT foundation models can capture imaging features relevant to disease phenotype characterization. Project page and code are available at: https://ricklisz.github.io/flexict.github.io and https://github.com/ricklisz/FlexiCT.

Reinforcement learning with verifiable rewards has become the standard recipe for improving LLM reasoning, but the dominant algorithm GRPO assigns a single trajectory-level advantage to every token, diluting the signal at pivotal reasoning steps and injecting noise at uninformative ones. Critic-free alternatives derived from on-policy distillation supply per-token signals through oracle-conditioned likelihood ratios, yet apply each signal in isolation from the trajectory-level evidence accumulated up to that position. We propose Oracle-Prompted Policy Optimization (OPPO), which rests on a single observation: the oracle signal used by prior distillation-style methods for local discrimination is also the natural Bayesian update of the model's belief about eventual success. Accumulating the signal along a trajectory yields, in closed form and at the cost of one extra forward pass, a running estimate of the success probability at every position, together with a token-level advantage that requires no learned value network and no additional rollouts. A first-order analysis factorizes the advantage into the per-token discrimination signal used by distillation methods modulated by a state weight that concentrates credit on genuinely pivotal tokens, with a directional variance-reduction guarantee. The framework admits two estimators differing only in which model scores the evidence: a \textit{self-oracle} that reuses the student and recovers the on-policy distillation reward as a strict special case, and a \textit{teacher-oracle} that delegates scoring to a stronger frozen model. On two base LLMs across seven mathematics, science, and code reasoning benchmarks, OPPO improves over GRPO, DAPO, and SDPO by up to $+6.0$ points on AMC'23 and $+5.2$ points on AIME'24, with gains that widen monotonically with response length.

Open-ended image generation is no longer a simple prompt-to-image problem. High-quality generation often requires an agent to combine a model's internal generative ability with external resources. As requests become more diverse and demanding, we aim to develop a general image-generation agent that can self-evolve through trajectories and use tools more effectively across varied generation challenges. To this end, we propose GenEvolve, a self-evolving framework based on Tool-Orchestrated Visual Experience Distillation. In GenEvolve, each generation attempt is modeled as a tool-orchestrated trajectory, where the agent gathers evidence, selects references, invokes generation skills, and composes them into a prompt-reference program. Unlike existing agentic generation methods that mainly rely on image-level scalar rewards, GenEvolve compares multiple trajectories for the same request and abstracts best-worst differences into structured visual experience, provided only to a privileged teacher branch. Inspired by on-policy self-distillation, Visual Experience Distillation provides dense token-level supervision, helping the student internalize better search, knowledge activation, reference selection, and prompt construction. We further construct GenEvolve-Data and GenEvolve-Bench. Experiments on public benchmarks and GenEvolve-Bench show substantial gains over strong baselines, achieving state-of-the-art performance among current image-generation frameworks. Our website is as follows: https://ephemeral182.github.io/GenEvolve/

Pretrained diffusion models serve as frozen teachers feeding downstream pipelines such as text-to-3D, single-step distillation, and data attribution. The teacher gradients these pipelines consume are Monte Carlo (MC) expectations over noise levels and Gaussian noise samples; their estimator variance dominates compute cost because each draw requires expensive upstream work (rendering, simulation, encoding). We introduce CARV, a compute-aware variance-accounting framework that motivates a hierarchical MC estimator: amortize the expensive upstream computation over cheap diffusion-noise resamples, sharpened by timestep importance sampling and a stratified-inverse-CDF construction. In our text-to-3D distillation and attribution experiments, CARV delivers 2-3x effective compute multipliers (most from amortized reuse; ~25% additional from IS+stratification) without changing the objective; in single-step distillation, the same techniques cut gradient variance by an order of magnitude but do not improve downstream FID, marking the regime where MC variance is no longer the bottleneck.

Currently, enhancing Unified Multimodal Models (UMMs) with image understanding, generation, and editing capabilities mainly relies on mixed multi-task training. Due to inherent task conflicts, such strategy requires complex multi-stage pipelines, massive data mixing, and balancing tricks, merely resulting in a performance trade-off rather than true mutual reinforcement. To break this paradigm, we propose Uni-Edit, an intelligent image editing task that serves as the first general task for UMM tuning. Unlike complex mixed pipelines, Uni-Edit improves performance across all three abilities at once using only one task, one training stage, and one dataset. Specifically, we first identify image editing as an inherently ideal general task, as it naturally demands both visual understanding and generation. However, existing editing data relies on simplistic instructions that severely underutilize a model's understanding capacity. To address this, we introduce the first automated and scalable data synthesis pipeline for intelligent editing, transforming diverse VQA data into complex and effective editing instructions with embedded questions and nested logic. This yields Uni-Edit-148k, pairing diverse reasoning-intensive instructions with high-quality edited images. Extensive experiments on BAGEL and Janus-Pro demonstrate that tuning solely on Uni-Edit achieves comprehensive enhancements across all three capabilities without any auxiliary operations.

Current end-to-end autonomous driving models are fundamentally constrained by the behavioral cloning ceiling of imitation learning. While reinforcement learning offers a path to smarter autonomy, it demands two missing pieces of infrastructure: (1) a cognitive foundation that understands traffic semantics and driving intent, and (2) a foresighted physical environment that can anticipate the consequences of candidate actions. To this end, we propose CoPhy, a CognitivePhysical reinforcement learning framework for autonomous driving. To distill to think, we distill VLM knowledge into the BEV encoder and then discard the VLM entirely, retaining cognitive ability at zero inference cost while releasing the cognitive channel as a pluggable interface for optional human language commands. To foresee to act, we build an auto-regressive BEV world model that explicitly predicts future semantic maps conditioned on candidate actions, serving as an interpretable physical sandbox from which safety metrics are directly derived. Built upon this dual infrastructure, we optimize the driving policy via GRPO with a novel dual-reward mechanism: a physical reward derived from BEV rollouts enforces hard safety constraints, while a cognitive reward from a language-aligned scorer ensures intent compliance. Extensive experiments demonstrate that CoPhy not only achieves state-of-the-art results on NAVSIM v1 and v2 benchmarks, but also enables safer driving via cognitively informed scene compliance and flexible intent control through user-defined language instructions.

The rapid progress of large language models (LLMs) is shifting semantic search toward a question-answering paradigm, where users ask questions and LLMs generate responses. In high-stake domains such as law, retrieval-augmented generation (RAG) is commonly used to mitigate hallucinations in generated responses. Nonetheless, prior work shows that RAG systems, whether general-purpose or legal-specific, still hallucinate at varying rates, making fine-grained evaluation essential. Despite the need, existing evaluation frameworks for legal RAG systems lack the granularity required to provide detailed analysis of retrieval and generation performance separately. Moreover, current benchmarks are largely English-only and centered on legal expert queries, overlooking non-expert needs. We introduce ClaimRAG-LAW, a comprehensive dataset for legal RAG that supports French and English, targets both experts and non-experts, and includes diverse question types reflecting realistic scenarios. We further apply a fine-grained evaluation framework of state-of-the-art legal RAG systems, revealing limitations in retrieval, generation, and claim-level analysis in the legal domain.

Sutra is a typed, purely functional programming language whose compiled forward pass is a PyTorch neural network. The compiler beta-reduces the whole program -- primitives, control flow, string I/O -- to one fused tensor-op graph over a frozen embedding substrate. Rotation binding, unbind, bundle, polynomial Kleene three-valued logic, and tail-recursive loops all lower to tensor operations; the Kleene connectives are Lagrange-interpolated polynomials exact on the {-1, 0, +1} truth grid. Validation is one fact tested two ways. (1) The same program runs on four frozen embeddings spanning two modalities -- three text encoders (nomic-embed-text, all-minilm, mxbai-embed-large) and one protein language model (ESM-2) -- and decodes bundles at 100% accuracy through width k=8 on every substrate, where the textbook Hadamard product has already collapsed (2.5% on mxbai-embed-large, 7.5% on all-minilm). (2) PyTorch autograd flows through the actually compiled graph: a fuzzy-rule classifier written in .su trains from random init (18.7 +/- 9.5%; chance = 20%, five classes) to 100.0 +/- 0.0% (three seeds) by backpropagating through the emitted graph, the symbolic source unmodified. A weighted variant additionally trains a scalar cosine gain and writes it back into the .su source as a numeric literal; recompiling reproduces the trained behaviour to ~2e-7 per logit, so the trained model is itself legible, recompilable code. The same artifact is therefore both a logic program and a trainable neural network.

Recent large language models support inputs of up to 10 million tokens, yet they perform poorly on long-context tasks that require complex reasoning. Such tasks can be solved using only a subset of the input -- a proxy context -- rather than the full sequence. Despite sharing the same underlying reasoning process, models exhibit a significant performance disparity between proxy and full contexts. To improve long-context reasoning, we propose ProxyCoT, a novel training framework that transfers reasoning capabilities from short proxy contexts to full long contexts. Specifically, we first obtain high-quality chain-of-thought reasoning traces on proxy contexts through reinforcement learning or distillation from a larger teacher model, and then ground the generated traces in full long contexts with supervised fine-tuning. Experiments across different datasets demonstrate that ProxyCoT consistently outperforms strong baselines with reduced computational overhead. Furthermore, models trained with ProxyCoT generalize their long-context reasoning capabilities to out-of-domain tasks.

Decentraland, a decentralized virtual reality platform operating within the expanding Metaverse ecosystem, utilizes its native MANA token to facilitate virtual asset transactions and governance. This study investigates the integration of Discord community sentiment with multi-modal financial data to enhance cryptocurrency price prediction within virtual world economies. We address: (1) identifying sentiment patterns within Decentraland's Discord community, and (2) evaluating the impact of multi-modal features on token return forecasting. Using a BERT-based large language model for sentiment analysis, we develop two LSTM architectures: a baseline incorporating historical prices and a multi-modal variant integrating sentiment scores, trading volume, and market capitalization. Results indicate predominantly neutral community sentiment with a positive skew. The multi-modal model significantly outperforms the price-only baseline in prediction accuracy. These findings demonstrate the predictive value of community-derived signals for virtual economy forecasting and establish a foundation for future research at the intersection of immersive virtual environments, natural language processing, and cryptocurrency market analysis.

Conversational AI has now reached billions of users, yet existing datasets capture only what people say, not what they think. We introduce ThoughtTrace, the first large-scale dataset that pairs real-world multi-turn human--AI conversations with users' self-reported thoughts: their reasons for sending prompts and reactions to assistant responses. ThoughtTrace comprises 1,058 users, 2,155 conversations, 17,058 turns, and 10,174 thought annotations collected across 20 language models. Our analysis shows that ThoughtTrace captures long-horizon, topically diverse interactions, and that thoughts are semantically distinct from messages, difficult for frontier LLMs to infer from context, diverse in content, and tied to conversation stages. We further demonstrate the utility of thoughts for downstream modeling. First, thoughts improve user-behavior prediction as inference-time context. Second, thought-guided rewrites provide fine-grained alignment signals for training personalized assistants. Together, ThoughtTrace establishes user thoughts as a new data modality for studying the cognitive dynamics behind human--AI interaction and provides a foundation for building assistants that better understand and adapt to users' latent goals, preferences, and needs.

Task vector composition has emerged as a promising paradigm for editing pre-trained models, enabling model merging through addition and unlearning through subtraction. Fine-tuning in the tangent space of a pre-trained model (linear fine-tuning) has proven effective, as it produces task vectors that are naturally disentangled and resistant to interference. However, linearized models suffer from limited expressivity during training and incur higher computational costs at inference time, which restrict their practical applicability. In this work, we bridge the gap between linear and standard non-linear fine-tuning. We show that linearity with respect to weight perturbations, a property defined in parameter space, can be enforced through constraints in activation space during training. Concretely, we distill hidden representations from a curvature-regularized linearized teacher into a non-linear student trained via conventional fine-tuning. We find that the resulting model inherits key properties of linearized models for task arithmetic, enabling effective composition of task vectors and achieving strong performance across vision and language benchmarks without incurring any inference-time overhead.

Wildfire prediction is important for early warning and resource allocation, yet existing Earth foundation models (Earth FMs) are pretrained for general atmospheric and geophysical objectives rather than wildfire forecasting. To address this gap, we introduce WILDFIRE-FM, the first foundation model pretrained specifically for wildfire prediction using weather, active-fire observations, topography, vegetation, and static environmental data. However, introducing a domain-specific backbone alone does not solve the evaluation problem: wildfire events are sparse in space and time, making transfer conclusions highly sensitive to matching rules and evaluation settings. To address this problem, we introduce a fixed-contract evaluation framework with two controlled checks: a fixed-output check for matching-rule effects and a fixed-feature check for head-selection effects. Under matched contracts, we compare WILDFIRE-FM with ten Earth-FM baselines across occupancy, spread, retrieval, and regression tasks. Our results show that wildfire transfer conclusions depend strongly on evaluation design and task formulation. We hope this framework and WILDFIRE-FM provide a foundation for future wildfire-specific Earth-FM research and benchmarking. Our code is available at https://anonymous.4open.science/r/Wildfire-fm-evaluation-contracts-5AE9/.

LLM routing matters most in long-horizon applications such as coding agents, deep research systems, and computer-use agents, where a single user request triggers many model calls. Routing each call to the cheapest sufficient model can cut costs without sacrificing quality, yet existing router benchmarks evaluate routers only on one-shot prompts. They never expose the router-visible prefix at an intermediate agent step, never test whether a cheaper replacement preserves downstream task success, and often rely on online LLM judges at evaluation time. We introduce TwinRouterBench, a step-level routing benchmark with two tracks. The static track provides 970 router-visible prefixes from 520 instances across SWE-bench, BFCL, mtRAG, QMSum, and PinchBench, each paired with an execution-verified target tier estimated under a released downgrade-and-cascade protocol; scoring is deterministic arithmetic over tier labels, trajectory membership, and token costs, with no online evaluator-side LLM judge. The dynamic track supplies a harness that runs routers on the full 500-case SWE-bench Verified suite; in this paper we report a 100-case held-out evaluation disjoint from the static SWE supervision split. At each LLM call the router selects a concrete model from a locked pool, and success is measured by official task resolution and realized API spend. The two tracks support fast offline iteration followed by end-to-end validation under live agent execution. Code and data are available at https://github.com/CommonstackAI/TwinRouterBench.

Ensemble disagreement is widely used as a proxy for epistemic uncertainty in medical image segmentation. In practice, many studies form ensembles via K-fold cross-validation (CV), yet refer to them as ``deep ensembles'' (DE). Because CV members are trained on different data subsets, their disagreement mixes seed-driven variability with data-exposure effects, which can change how uncertainty should be interpreted. We audit recent segmentation uncertainty studies and find that terminology--implementation mismatches are common. We then compare a standard 5-fold CV ensemble to a 5-member DE (fixed training set, different random seeds) under otherwise identical configurations on three multi-rater segmentation datasets spanning three modalities. We evaluate uncertainty for calibration, failure detection, ambiguity modeling, and robustness under distribution shift. DE match segmentation accuracy while improving calibration and failure detection, whereas CV ensembles sometimes correlate more strongly with inter-rater variability on the studied datasets. Thus, ensemble construction should be chosen to match the research question: DE for reliability-oriented use (e.g., selective referral/failure detection) and CV ensembles as a proxy for ambiguity. We provide a lightweight nnU-Net modification enabling DE training within the default pipeline.

Coding agents are increasingly used as application builders, yet many evaluations still focus on source code, repository-level tests, or intermediate traces rather than the delivered application. We introduce WebGameBench, a requirement-to-application benchmark that evaluates whether coding agents can turn a frozen Structured WebGame Specification into a browser-accessible game. Browser-native games provide a compact but behavior-dense testbed: even simple games require coordinated input handling, spatial mapping, rule execution, state transitions, terminal conditions, restart behavior, and visible feedback. In WebGameBench, each generated artifact is built, served, and exposed as a browser-accessible application under a unified deployment protocol. A runtime evaluator then interacts with the delivered game in a real browser and assigns a three-way label: EXCELLENT, USABLE, or UNUSABLE. On a human-reviewed subset, the runtime label is broadly aligned with human gameplay review under the Usable-rate criterion. Across 111 tasks, 12 coding agents, and 14 evaluation configurations, WebGameBench separates current systems: the best configuration reaches a 76.9% usable rate but only a 20.2% excellent rate. This gap shows that crossing the minimum playable-delivery threshold is still far from complete requirement satisfaction. To our knowledge, WebGameBench is the first requirement-to-application benchmark for browser-native game delivery that validates delivered-application runtime labels against independent human gameplay review under the Usable-rate criterion.

We address concurrency control for LLM agents sharing mutable state over HTTP, where agents cannot be modified to declare read sets. S-Bus is an HTTP middleware whose central mechanism, a server-side DeliveryLog, reconstructs each agent's read set at commit time from observed HTTP GET traffic. The consistency property it provides -- Observable-Read Isolation (ORI), a partial causal consistency over the HTTP-observable read projection -- prevents Structural Race Conditions in dedicated-shard topologies. Three contributions. (C1) DeliveryLog mechanism with three-tier mechanised evidence: TLAPS proves ReadSetSoundness and ORICommitSafety (modulo one typing axiom); exhaustive TLC at N=3 explores 20,763,484 states with zero violations; Dafny discharges 9 inductive lemmas. (C2) Empirical safety parity against PostgreSQL 17 SERIALIZABLE and Redis 7 WATCH/MULTI: zero Type-I corruptions across 884,110 commit attempts (427,308 under active contention). (C3) ORI is semantically neutral in dedicated-shard workloads but harmful in single-shard collaborative writing because preservation propagates concurrent contradictions. v2 update: the PH-3 LLM judge is now independently validated against a human annotator (Zahid Hussain, Mindgigs Peshawar) on 400 (step, shard) pairs at strict kappa=0.93 (n=93, 96.8% raw agreement). Inter-LLM-judge agreement is kappa=0.46 (boundary variance). Agent self-reports over-claim shard usage by 32% (LLM judge) to 49% (human annotator). The SJ-v4 semantic-quality rubric remains single-judge LLM-only. Source code, formal proofs, harness, annotation data: https://github.com/sajjadanwar0/sbus

Recent advances in molecular representation integrates molecular topological and visual modalities, opening new avenues for precise Molecular Relational Learning (MRL). Existing MRL methods focus on intra-domain modeling, and their inherent domain-closed effect limits applicability to molecular science, particularly in elucidating cross-domain interaction mechanisms. Consequently, the imperative for Cross-Domain Molecular Relational Learning has become increasingly pressing. Benefiting from structure-activity analysis, we propose the Domain Adversarial Training Network with Structural-Semantic Transfer Discrepancy (DisTrans) to optimize cross-domain adaptive representation for molecular structures and visual images. 1) We employ the gradient reversal strategy based on substructure topological discrepancies between domains to learn the domain dependence of molecular structures. This strategy guides the model to adapt to the structural adjacency patterns in the target domain, generating domain-separable structural representations. 2) We apply the cross-domain representation guidance mechanism to align the functional-group semantic information between the source and target domains, learning cross-domain consistency information. The experimental results in two typical cross-domain strategies demonstrate that DisTrans outperforms 16 baseline methods, maintaining satisfactory performance even under pronounced inter-domain discrepancy.