arXiv:2604.01187v3 Announce Type: replace-cross
Abstract: When competing species grow into new territory, the population is dominated by descendants of successful ancestors at the expansion front. Successful ancestry depends on both the reproductive advantage (fitness), as well as ability and opportunity to colonize new domains. We present a model that integrates both elements by coupling the classic description of one-dimensional competition (Fisher equation) to the minimal model of front shape (KPZ equation). Macroscopic manifestations of these equations are distinct growth morphologies controlled by expansion rates, competitive abilities, or spatial anisotropy. In some cases the ability to expand in space may overcome reproductive advantage in colonizing new territory. When new traits appear with accumulating mutations, we find that variations in fitness in range expansion may be described by the Tracy--Widom distribution.
Science Journals
arXiv:2605.30333v1 Announce Type: new
Abstract: A plausible future mathematical claim must satisfy two constraints: it should follow the direction of prior work and respect the formal dependencies that constrain what can validly follow. Existing approaches typically model only one of these sources, producing claims that are either weakly grounded or insufficiently motivated. We introduce grounded future mathematical generation, where the goal is to generate a plausible future theorem-like claim for an anchor paper using two complementary sources of context: its scientific citation graph and aligned formal theorem dependency graph. To address this setting, we propose COMPOSE, a dual-graph framework that conditions a language model on both scientific citation context and formal theorem structure. To support this setting, we construct a dataset of 108K paired scientific-formal graph examples from arXiv and Mathlib, together with a benchmark of 47K future papers from 2024--2025. Experiments show that COMPOSE outperforms strong baselines on retrieval to real future papers and achieves the best overall performance under LLM-judge evaluation, producing more grounded and mathematically richer outputs. These results show that future mathematical generation benefits from combining scientific context with formal structure. Project page is available at https://david-busbib.github.io/COMPOSE-page/.
arXiv:2605.29538v1 Announce Type: new
Abstract: With the emergence of wireless applications in three-dimensional environments, such as the low-altitude airspace and 3D heterogeneous networks, radio map estimation is increasingly required to characterize signal propagation across both horizontal and vertical dimensions. However, extending radio map estimation from 2D to 3D remains challenging due to increased spatial sparsity and limited supervision across continuous altitudes. In this paper, we propose \textbf{\textit{RadioFormer3D}}, a specialized model for volumetric spectrum reconstruction under weak supervision. Building on the dual-stream, multi-granularity fusion architecture of \textit{RadioFormer}, \textit{RadioFormer3D} introduces a Fourier-based sampling encoder and a volumetric decoder to efficiently process sparse measurements in 3D space. To alleviate the lack of vertical supervision, we propose the \textbf{\textit{Joint Spectrum Integrity Loss}}, which integrates volume-level pseudo-label supervision, map-level geometry-aware radio rendering, and pixel-level localized constraints within a unified optimization scheme. This design enables the model to capture complex vertical structural relationships more effectively under sparse supervision. Extensive experiments across several radio map datasets show that \textit{RadioFormer3D} achieves superior overall performance compared to representative existing methods. In particular, it demonstrates improved reconstruction quality at unlabeled altitudes while maintaining a favorable trade-off between accuracy and inference efficiency, positioning it as a highly promising solution for future 3D environment-aware wireless networks.
arXiv:2605.27078v2 Announce Type: replace
Abstract: Training loss and accuracy are the standard signals used to monitor generalization during deep neural network training. Two well-documented phenomena complicate this picture: in grokking, train loss falls rapidly while test performance improves abruptly only after a long delay; in epoch-wise double descent, train loss decreases monotonically while test loss or error rises and falls. Existing accounts are often task-specific, and a task-agnostic analysis framework for diagnosing and explaining these phenomena across realistic tasks and architectures is missing. We address this challenge by analyzing two competing processes that underlie learning dynamics: representation learning in the encoder and readout calibration in the final classifier. Using tools from representational geometry, neural tangent kernels, and linear probing, we show that both processes are active throughout training, with the fluctuations of their relative speed giving rise to seemingly anomalous generalization dynamics. Applying the representation-readout decomposition to grokking across a wide range of tasks and architectures, we find that the readout is train-biased before grokking onset, and representation learning is gradual but not absent, contrary to the lazy-to-rich account. The framework further provides diagnostic signatures distinguishing spurious from genuine generalization: in a previously reported MNIST grokking example and an epoch-wise double descent example, apparent delayed or non-monotone generalization is shown to arise from representation degradation and readout misalignment induced by non-standard training recipes. Together, these results establish the representation-readout decomposition as a top-down framework for understanding learning dynamics and revealing underlying algorithms for interpretability research.
arXiv:2605.26815v2 Announce Type: replace-cross
Abstract: Let $G_n$ be the coprime graph on $\{1,\ldots,n\}$. We prove that the mixed vertex-coloring coprime Ramsey number satisfies \[
\Rcop(k_1,\ldots,k_c)=p_{\sum_{i=1}^c(k_i-1)}, \] where $p_m$ is the $m$-th prime. The proof is elementary: the prime clique $\{1\}\cup\{p\le n:p\text{ prime}\}$ gives the upper bound by pigeonhole, while a prime-bin partition gives the matching lower bound by coloring each composite with a bin containing one of its prime divisors. We reserve $\Rcop$ for this vertex-coloring parameter; the edge-coloring parameter on the same host graph is denoted $\Redge$. The same certificate viewpoint yields several extensions, including a support-disjointness generalization, a polynomial-time certificate-extraction primitive, and an exact reduction of the edge-coloring variant to classical Ramsey numbers: $\Redge(k_1,\ldots,k_c)=p_{\Rcl(k_1,\ldots,k_c)-1}$. These two formulas are rank transfers from the same clique-label certificate. We also prove that the balanced two-color diagonal threshold equals the unrestricted threshold $p_{2k-2}$ for all $k\ge2$, via a deterministic prime-bin split requiring only the weak inequality $2p_m<p_{2m}<3p_m$; for fixed $c$, a Hall argument plus a standard Selberg--Delange estimate gives eventual multicolor balanced certificates.
arXiv:2602.03357v2 Announce Type: replace
Abstract: This paper proposes FedNMap, a normal map-based method for composite federated learning, where the objective consists of a smooth loss and a possibly nonsmooth regularizer. FedNMap leverages a normal map-based update scheme to handle the nonsmooth term and incorporates a local correction strategy to mitigate the impact of data heterogeneity across clients. Under standard assumptions, including smooth local losses, weak convexity of the regularizer, and bounded stochastic gradient variance, FedNMap achieves linear speedup with respect to both the number of clients and the number of local updates for nonconvex losses, both with and without the Polyak-{\L}ojasiewicz condition. To the best of our knowledge, this is the first algorithm establishing linear speedup for nonconvex composite federated learning. Numerical experiments corroborate our theoretical findings and demonstrate the linear speedup of FedNMap.
arXiv:2605.29971v1 Announce Type: new
Abstract: Causal interventions in language model representations have largely targeted discrete features, like grammatical number. However, language models must also make use of features that are graded. We introduce a method for causal intervention on continuous variables: given activation vectors paired with a graded target variable, we localize a low-dimensional direction for that variable and use this direction to edit a vectors toward counterfactual target values. We apply this method to a continuous feature that is well-studied in psycholinguistics, namely verb bias (which reflects which syntactic structures tend to follow a given verb). We show that verb bias is causally represented in steering vectors extracted from large language models: counterfactual edits to verb bias systematically shift downstream structural preferences. Verb bias has also previously been linked to in-context learning; in further analyses, we find that steering vectors encode error signals that could drive the error-driven update behavior seen in in-context learning but that these aspects of the steering vectors are not causally used in downstream production. Overall, these results show causal interventions can be applied to continuous variables, though connecting continuous variables to in-context learning remains a challenge.
arXiv:2605.29927v1 Announce Type: new
Abstract: Despite recent advances, LLM-based web agents still struggle with limited exploration, omission of critical steps, and sensitivity to task constraints. Prior work suggests that many of these failures stem from weaknesses in planning, yet the impact of alternative natural language plan representation remains unexplored. To address this, we introduce PlanAhead, a static planner-executor framework that evaluates the impact of plan representation in agent performance. We first automatically categorize WebArena tasks into 3 difficulty levels, enabling consistent difficulty grading without human annotation. Then we systematically evaluate 4 different plan representations on the tasks categorized as hard: sequential subgoals, narrative, pseudocode, and checklist; across different families of multimodal LLM powered agents (OpenAI, Alibaba, and Google). To account for stochastic variability, we introduce two novel evaluation metrics: Achievement Rate (AR) and Solved-Task Consistency (STC). Our results show that both, the plan formulation and the underlying LLM generating the plan, significantly influence web-agent robustness and task success.
arXiv:2605.30024v1 Announce Type: new
Abstract: Standard EU energy system modelling approaches optimize for least-cost, leading to highly centralized systems, in conflict with political feasibility and physical security concerns. This paper incorporates decentralisation as a constraint in a European energy system model using a novel, linear load-weighted renewable capacity constraint, the K-parameter, which scales with total system renewable capacity to avoid interference with decarbonisation targets. The model is a 37-node electricity-only brownfield system based on the PyPSA-EUR framework, with projected 2050 loads and technology costs. A total of 105 optimized scenarios are analyzed at 14 levels of decarbonization and 8 levels of decentralization. Full decarbonization leads to an 80% cost increase due to, among other factors, a 78% increase in energy generation capacity. Without decentralisation constraints, system equity initially improves but collapses at high decarbonisation levels due to concentration in regions with optimal renewable resources. Moderate decentralization of K=7 achieves 76% of the equity benefits at only a 9% cost increase compared to K=1. This indicates that moderate decentralization can be a viable strategy to balance societal preferences and cost-efficiency in the European energy transition.
arXiv:2509.17208v3 Announce Type: replace
Abstract: Machine-learned coarse-grained (CG) potentials are fast, but degrade over time when simulations reach under-sampled bio-molecular conformations, and generating widespread all-atom (AA) data to combat this is computationally infeasible. We propose a novel active learning (AL) framework for CG neural network potentials in molecular dynamics (MD). Building on the CGSchNet model, our method employs root mean squared deviation (RMSD)-based frame selection from MD simulations in order to generate data on-the-fly by querying an oracle during the training of a neural network potential. This framework preserves CG-level efficiency while correcting the model at precise, RMSD-identified coverage gaps. By training CGSchNet, a coarse-grained neural network potential, we empirically show that our framework explores previously unseen configurations and trains the model on unexplored regions of conformational space. Our active learning framework enables a CGSchNet model trained on the Chignolin protein to achieve a 33.05\% improvement in the Wasserstein-1 (W1) metric in Time-lagged Independent Component Analysis (TICA) space on an in-house benchmark suite.
arXiv:2508.16873v3 Announce Type: replace
Abstract: Understanding how visual content conveys sentiment is increasingly important in a digital landscape dominated by imagery. However, sentiment perception depends on complex scene-level semantics, making this a challenging task for computational models. This paper examines how Multimodal Large Language Models (MLLMs) perform sentiment analysis in images through a systematic, evaluation-driven study encompassing three perspectives: (i) direct sentiment classification from images using MLLMs; (ii) sentiment analysis on MLLM-generated descriptions using pre-trained LLMs; and (iii) fine-tuning these LLMs on sentiment-labeled descriptions to assess performance and generalization. Experiments on a recent benchmark show that a two-stage MLLM description-mediated pipeline can substantially improve prediction accuracy under several evaluation settings, particularly when the LLM component is fine-tuned. Across different agreement thresholds and sentiment granularities, the strongest configurations of this pipeline outperform lexicon-, CNN-, and Transformer-based baselines in our benchmark by up to 30.9%, 64.8%, and 42.4%, respectively. In cross-dataset evaluation, the proposed pipeline - without training or fine-tuning on the target dataset - still surpasses the best in-domain baseline by over 8%. Overall, the study provides a comprehensive assessment of MLLM description-mediated sentiment analysis, clarifying the conditions under which it is effective, the scenarios in which it fails, and its comparison with traditional vision-based approaches, while also providing a reproducible benchmark resource for future research.
arXiv:2508.12176v2 Announce Type: replace
Abstract: Radio Frequency (RF) sensing has emerged as a powerful, privacy-preserving alternative to vision-based methods for various perception tasks. However, building high-quality RF datasets in dynamic and diverse environments remains a major challenge. To address this, we introduce WaveVerse, a prompt-based, scalable framework that simulates realistic RF signals from generated indoor scenes with human motions guided by spatial paths, enabling diverse and feasible behaviors without manual trajectory design. WaveVerse features a language-guided 4D world generator and a physics-based signal simulator that enables realistic simulation of RF signals in diverse environments. It employs a phase-coherent ray tracer that preserves both spatial and temporal phase consistency. The simulated signals show high fidelity on phase-sensitive benchmarks, and closely align with both real-world collected measurements and simulations from a proprietary electromagnetic solver. When used for data augmentation, WaveVerse consistently improves performance in downstream tasks like RF imaging and human activity recognition, with gains that grow with the amount of simulated data and surpass existing methods. Code and additional materials are available on the webpage.
arXiv:2511.21847v3 Announce Type: replace
Abstract: Here we demonstrate that the time-evolving interface observed during droplet formation, and consequently the resulting morphology nearing pinch-off, encode sufficient physical information for machine-learning (ML) frameworks to accurately infer key fluid properties, including viscosity and surface tension. Snapshots of dripping drops at the moment of break-up, together with their liquid properties and the flow rate, are used to form a data set for training ML algorithms. Experiments consisted of visualizing, using high-speed imaging, the process of droplet formation and identifying the frame closest to break-up. Experiments were conducted using Newtonian fluids under controlled flow conditions. In terms of the Reynolds (Re) and Ohnesorge (Oh) numbers, our conditions cover the domains 0.001< Re< 200 and 0.01 < Oh < 20, by using silicon oils, aqueous solutions of ethanol and glycerin, and methanol. For each case, flow parameters were recorded, along with images capturing the final stages of droplet break-up. Supervised regression models were trained to predict fluid parameters from the extracted contours of the breaking droplets. Our data set contains 840 examples. Our results demonstrate that the droplet geometry at pinch-off contains sufficient information to infer fluid properties by machine learning approaches. Our methods can predict surface tension, viscosity, or the droplet shape at pinch-off. These approaches provide alternatives to conventional methods to measure liquid properties while reducing measurement complexity and evaluation time and facilitating integration into automation. Unsupervised clustering is performed; the clusters represent regions in the Re-Oh and Bo-Oh planes, indicating that the latent representation may reveal physical properties and offering insight into droplet dynamics.
arXiv:2605.30014v1 Announce Type: new
Abstract: Urban trajectories play a crucial role in modeling urban dynamics and supporting various smart city applications. However, privacy concerns restrict access to large-scale and high-quality trajectory datasets. Trajectory generation provides a promising alternative by synthesizing realistic data to mitigate privacy risks. However, existing methods fail to explicitly capture travel patterns and can only generate fixed-length trajectories under a single condition. To address these limitations, we propose \textbf{HTP}, which \textbf{H}ierarchically generates \textbf{T}ravel patterns first and then generates GPS \textbf{P}oints by using large language models (LLMs), rather than directly generating GPS points. We first design a trajectory-specific residual quantization variational autoencoder (RQ-VAE) that quantizes micro-level GPS trajectories into compact, macro-level travel pattern tokens in a coarse-to-fine manner. These tokens capture rich segment spatial irregularities, such as point density variations caused by traffic conditions. Then, we extend the LLM vocabulary with travel pattern tokens to align trajectory representations with the LLM input, and apply supervised fine-tuning (SFT) to align the LLM with the trajectory generation task, enabling generation of travel pattern sequences under various conditions. Extensive experiments on two real-world datasets show that HTP outperforms the strongest baseline by an average of 29.78\% in terms of generation quality. Our code is available at https://github.com/slzhou-xy/HTP.
arXiv:2605.29988v1 Announce Type: new
Abstract: Safety applications in vehicle-to-everything communications and Cooperative Intelligent Transport Systems rely on reliable and timely message exchange, which in turn depends on accurate modeling of wireless signal propagation. Simulation frameworks such as VEINS are widely adopted to design and evaluate such systems before deployment; however, their realism strongly depends on the validity of the underlying channel and antenna models. This work presents an empirical validation of the VEINS simulator against real-world data collected from the MASA living laboratory. Using the default configuration, we compare Received Signal Strength Indicator (RSSI), number of messages, and attenuation of the signal. The results show that VEINS systematically overestimates the RSSI value, while losing approximately 18% of the total number of messages received compared to the MASA, revealing inconsistencies between simulation and reality. The contribution of this study is a direct comparison between simulated and real world data, establishing a quantitative basis for future calibration of VEINS parameters to improve the fidelity of VANET simulations in C-ITS safety research.
arXiv:2605.29979v1 Announce Type: new
Abstract: The behavior of LLMs does not depend solely on the model itself. Components of the inference system, such as the inference engine, attention backend, and hardware platform, subtly influence how inputs are processed. These components differ in their implementations and thereby induce small numerical deviations across systems when running the same model. While prior work has established the theoretical existence of such deviations, their security implications have remained unexplored. In this paper, we show that these deviations are characteristic of specific components and propagate to observable textual outputs, exposing the inference system to any party that can query the model. Building on this observation, we introduce a fingerprinting method that analyzes the prompt-response behavior of LLMs to identify components of the inference system. Our empirical evaluation demonstrates that the inference engine, attention backend, and underlying hardware platform can be identified reliably, even when the LLM is operated at non-zero temperature. We show that preventing fingerprinting is fundamentally hard, as it would require eliminating numerical differences between hardware and software stacks. We therefore propose partial mitigations and discuss their impact.
arXiv:2605.27379v2 Announce Type: replace
Abstract: We present Soro, a family of Tajik-specialized conversational large language models (LLMs) designed for real-world deployment under tight compute and connectivity constraints in Tajikistan. Starting from open-weight Gemma 3 checkpoints, we perform Tajik-only continual pretraining on a curated 1.9-billion-token corpus spanning filtered web text, PDF documents, and curriculum-aligned educational materials, followed by supervised instruction tuning on 40K Tajik teacher-style examples. To enable rigorous evaluation despite the limited coverage of Tajik in standard benchmarks, we introduce a suite of Tajik benchmarks covering general knowledge, linguistic competence, and school- and university entrance-exam domains, and we open-source them on Hugging Face. Across these Tajik benchmarks, Soro substantially outperforms same-size Gemma 3 baselines while retaining strong English performance on standard datasets. We further show that FP8 and INT4 quantization of Soro preserves most Tajik-language gains while reducing memory requirements for edge deployment, supporting an ongoing education-sector pilot and planned scale-out across schools in Tajikistan.
arXiv:2508.08677v2 Announce Type: replace
Abstract: Online Class-Incremental Learning (OCIL) enables models to learn continuously from non-i.i.d. data streams. Since samples of the data streams can be seen only once, it is more suitable for real-world scenarios compared to offline learning. However, this constraint intensifies the challenge for OCIL in maintaining an appropriate balance between stability and plasticity. Moreover, under stricter memory buffer constraints in real world, current replay-based methods are less effective. While ensemble methods improve plasticity, they often struggle with stability. Inspired by the Global Workspace Theory (GWT), we propose a novel approach that enhances ensemble learning through a Global Workspace Model (GWM)-a shared, implicit memory that guides the learning of multiple student models. The GWM is formed by fusing the parameters of all students within each training batch, capturing the historical learning trajectory and serving as a dynamic anchor for knowledge consolidation. Like the broadcasting mechanism of GWT, the GWM is redistributed periodically to students, stabilizing learning and promoting cross-task consistency. In addition, we introduce a multi-level collaborative distillation mechanism. It enforces peer-to-peer consistency among students and preserves historical knowledge by aligning each student with the GWM. As a result, student models remain adaptable to new tasks while maintaining previously learned knowledge, striking a better balance between stability and plasticity. Extensive experiments on three standard OCIL benchmarks show that our method delivers significant performance improvement for several OCIL models across various memory budgets. The code is available at https://github.com/susususushi/GWM.
arXiv:2508.05614v2 Announce Type: replace
Abstract: LLM agents achieve 85-96% success on tasks where instructions fully specify the action, but drop to 29-53% when action feasibility depends on environmental state that the instruction does not mention. We argue that this gap reflects a missing capability: action grounding, the ability to infer from structured environmental state whether an action is feasible, what prerequisites it lacks, and whether it exceeds individual capacity. We introduce GroundAct, a benchmark of 1,500 scenarios and 16,592 task instances in text-based interactive environments spanning 11 domains, with tasks organized into seven categories along a cognitive complexity hierarchy. Evaluating 15 LLMs (3B-671B), we find three diagnostic patterns: (i) attribute reasoning is weakly correlated with tool and coordination reasoning, producing distinct model profiles; (ii) complete environment graphs yield up to +27.6/-22.9% on tool use vs. implicit collaboration, separating search-bound from constraint-filtering bottlenecks; and (iii) supervised fine-tuning lifts Qwen2.5-3B from 0.6% to 76.3% on direct command but only 1.5% to 5.5% on implicit collaboration. These results establish action grounding as a multi-dimensional challenge irreducible to scaling.
arXiv:2605.02116v3 Announce Type: replace
Abstract: Contrastive representation learning (CRL) underpins many modern foundation models. Despite recent theoretical progress, existing analyses suffer from several key limitations: (i) the statistical consistency of CRL remains poorly understood; (ii) available generalization bounds deteriorate as the number of negative samples increases, contradicting the empirical benefits of large negative sets; and (iii) the retrieval performance of CRL has received limited theoretical attention. In this paper, we develop a unified statistical learning theory for CRL. For downstream tasks, we evaluate retrieval quality using an AUC-type population criterion and show that the contrastive loss is \emph{statistically consistent} with optimal ranking. We further establish a \emph{calibration-style inequality} that quantitatively relates excess contrastive risk to excess retrieval suboptimality. For upstream training, we study both supervised and self-supervised contrastive objectives and derive generalization bounds of order $O(1/m + 1/\sqrt{n})$ and $O(1/\sqrt{m} + 1/\sqrt{n})$, respectively, where $m$ denotes the number of negative samples and $n$ the number of anchor points. These bounds not only explain the empirical advantages of large negative sets but also reveal an explicit trade-off between $m$ and $n$. Extensive experiments on large-scale vision--language models corroborate our theoretical predictions.
arXiv:2605.29174v1 Announce Type: new
Abstract: DeFi investment agents, systems that use AI for autonomous on-chain trading, have attained over USD 3 billion in combined token valuations since late 2024. We survey over 1,900 AI-tagged crypto projects, filter to investment-focused agents, and curate 10 representative projects spanning strategy and observability dimensions. We then conduct a deep-dive architectural analysis of two prominent agent frameworks, ElizaOS and Virtuals Protocol, and a quantitative on-chain performance analysis of 11 Solana-based agent treasuries with publicly attributable trading activity, covering 925,323 token holders. We find that current deployments remain early and heterogeneous: (1) in our sample, many projects do not yet provide clear evidence of autonomous trade execution, and developer interviews suggest that many visible deployments remain basic API integrations; (2) agent treasuries retain over USD 30M in paper gains while token holders collectively lost USD 191.7M, with the top 1% of wallets capturing 81.4% of all gains (USD 1.81B); (3) token valuations are weakly connected to treasury fundamentals, with market-cap-to-AUM ratios exceeding 10,000x versus below 1x for established DeFi protocols; and (4) aggregate user gains peaked at USD 2.4B before declining to net losses, with median returns negative on every platform and tokens declining 93% on average from all-time highs. We interpret these outcomes as characteristic of a permissionless, first-generation market in which open infrastructure enables rapid experimentation but also allows naive or speculative agents to launch before robust standards for autonomy, performance, and stakeholder alignment emerge. We therefore propose a maturity framework along three dimensions: autonomous execution, risk-adjusted profitability, and stakeholder alignment, to characterize the gap between current deployments and future investment-grade agent systems.
arXiv:2605.29585v1 Announce Type: new
Abstract: Vision-language models (VLMs) are increasingly used to answer questions about physical scenes, yet most evaluations reduce performance to a final answer. This hides whether the model perceived the right objects, represented the right physical state, predicted a plausible transition, or merely selected the right option for the wrong reasons. We introduce \wmw, an evaluation framework for auditing the \emph{language-expressed physical commitments} of VLMs. Instead of scoring only $I,q\mapsto a$, we ask models to produce a typed trace $I,q\mapsto(s_0,\Delta s,s_1,a)$: an initial state, a state transition, a resulting state, and an answer. A hybrid verifier then checks schema validity, state grounding, transition consistency, and answer-trace compatibility, yielding typed error labels such as object, relation, force, transition, temporal, unit/scale, and faithfulness errors. We release \tracebank, a controlled trace resource with \nSeed schema- and recomputation-validated synthetic scenarios across \nFamilies physics families, \nPairs minimally perturbed contrastive preference pairs, verifier code, audit guidelines, and model outputs. We evaluate \nModels VLMs on both controlled and external physical-reasoning examples. \wmw reveals failures that answer-only evaluation misses: 35\% of correct answers from mid-tier models are backed by physically invalid traces. Verifier-guided reranking recovers up to 7 percentage points of trace validity without sacrificing answer accuracy, and trace-level preference tuning reduces hidden inconsistency by 41\% relative. The contribution is not another final-answer physics benchmark, but a reusable protocol for measuring whether a VLM's stated physical world can be true at the same time as its answer.
arXiv:2412.00452v3 Announce Type: replace
Abstract: Conventional federated learning (FL) heavily depends on high-quality labels, which are often impractical in the real world, leading to the federated label-noise (F-LN) problem. Worse still, the F-LN problem is exacerbated by the heterogeneity of FL, whereas clients experience different label-noise types, ratios, and data distribution. In this study, we first observe an intriguing phenomenon that the global model of FL exhibits a slow memorization of noisy labels, suggesting its ability to maintain reliable predictions and robust representations in FL. Motivated by this, we propose a novel method termed Federated Global Reviser (\method), a straightforward yet effective method comprising three modules that collaboratively rectify noisy labels and regularize local training. By exploiting this inherent property, \method\ improves the label-noise robustness of FL in a self-contained manner. Extensive experiments on three widely used F-LN benchmarks demonstrate the superior performance of FedGR, consistently outperforming eight state-of-the-art baselines even in severe label-noise and data heterogeneity. Code: https://github.com/cs-yuxintian/FedGR-ICML26
arXiv:2605.29568v1 Announce Type: new
Abstract: Tool-Integrated Reasoning (TIR) extends LLM capabilities by leveraging external environments. However, existing methods lack the deliberation during sequential tool invocation required for strategic planning and self-correction. While RL mitigates this, conventional approaches for Tool-Integrated Reasoning are hindered by sparse outcome-based rewards, failing to supervise intermediate reasoning steps and tool invocations. To address this, we propose DeepTool, a novel framework that scales deliberate thinking within the interleaved process of thinking, action, and observation at each turn. In DeepTool, we first introduce a synthesis pipeline that evolves extended thinking into interleaved trajectories, integrating adversarial perturbations to ensure robustness and self-correction. Secondly, we devise Process-Supervised Reinforcement Learning based on GRPO, which utilizes an Action-Centric Process Reward to reinforce intermediate interleaved thinking and enforce precise tool invocation at every turn. Extensive experiments demonstrate that DeepTool achieves superior performance, boosting Qwen2.5-7B significantly across six benchmarks (e.g., AIME24: 3.2% -> 40.4% and HMMT25: 0.0% -> 28.6%). Furthermore, the token cost-effectiveness analysis confirms the utility of interleaved thinking, demonstrating DeepTool's optimal balance between performance and token efficiency.
arXiv:2605.30342v1 Announce Type: new
Abstract: We present Gaussian Splatting Anisotropic Visibility Field (GAVIS), a novel framework for uncertainty quantification and active mapping in 3DGS. Our key insight is that regions unseen from the training views yield unreliable predictions from the 3DGS. To address this, we introduce a principled and efficient method for quantifying the visibility field in 3DGS, defined as the anisotropic visibility of each particle with respect to the training views, and represented using spherical harmonics. The resulting visibility field is integrated into a Bayesian Network-based uncertainty-aware 3DGS rasterizer, enabling real-time (200 FPS) uncertainty quantification for synthesized views. Active mapping is further performed within a maximum information gain framework building on this formulation. Extensive experiments across diverse environments demonstrate that GAVIS consistently and significantly outperforms prior approaches in both accuracy and efficiency. Moreover, beyond standalone use, our method can be applied post-hoc to improve the performance of existing approaches.