arXiv:2607.12389v1 Announce Type: cross
Abstract: We consider Bayesian bandit models and prove that Thompson sampling makes at most twice the expected number of mistakes (selections of a suboptimal arm) as any other policy. Our analysis applies as long as the latent arm processes are independent and each arm evolves only when played. For stochastic bandits with best arm defined via mean reward, this confirms a conjecture of Guha and Munagala from 2014, where the factor $2$ is already best possible. The result holds under any nonincreasing sequence of round weights, including fixed horizon and geometric discounting.
Science Journals
arXiv:2602.11198v2 Announce Type: replace
Abstract: Multi-agent frameworks (MAFs) promise to simplify LLM-driven software development, yet no principled metric captures how well AI coding assistants can generate correct, framework-specific code. We introduce \textit{AI-assistability} ($\mathcal{AI}$), a composite metric that quantifies a framework's amenability to AI-assisted development by combining structural alignment ($\bar{\sigma}$) with functional correctness (pass@1). To evaluate this metric in a controlled setting, we design DDL2PropBank, a novel benchmark task that maps relational database schemas to PropBank semantic rolesets, and implement identical agent logic across ten frameworks using the Agent-as-a-Tool pattern. Our results challenge the intuition that declarative framework design guarantees AI-assistability: Agno, with a single canonical pattern and convention-aligned API, achieves the highest $\mathcal{AI}$ score (0.55), while DSPy -- the most declarative framework by design -- scores lowest (0.07), as its novel abstractions are insufficiently represented in AI training data. We find that convention alignment, not declarative design alone, is the primary driver of AI-assistability ($r = 0.576$ between $\bar{\sigma}$ and pass@1). All artifacts -- DDL2PropBank, PropBank MCP server, and all implementations -- are available at https://github.com/ahmeshaf/ddl2propbank
arXiv:2607.12764v1 Announce Type: new
Abstract: Retrieval-augmented generation (RAG) has emerged as a critical paradigm for grounding Multimodal Large Language Models (MLLMs) in external knowledge. Recent GraphRAG methods introduce structured entity-relation graphs to improve retrieval and reasoning. However, they remain limited by treating knowledge graphs as static data structures built offline and queried in a single pass. This static paradigm misaligns with the interactive, iterative nature of knowledge-intensive reasoning, creating three bottlenecks: (i) text-centric fragmentation that impedes cross-modal reasoning, (ii) frozen structures unable to incorporate new evidence or correct errors, and (iii) rigid single-pass retrieval without adaptive refinement. To overcome these limitations, we introduce EvoGraph-R1, a self-evolving GraphRAG framework that reconceptualizes knowledge graphs as dynamic environments shaped through agent interactions. We formulate retrieval as a Markov Decision Process (MDP) where the agent observes the graph state and executes actions to query (GraphRetrieve), expand (WebSearch), refine (GraphEdit), or terminate (Answer) the reasoning. These actions reshape the hypergraph structure and generate feedback signals that guide subsequent evolution. Through this closed loop, the hypergraph evolves by integrating new evidence, correcting errors, and refining structure to support multi-hop reasoning. Experiments on multimodal VQA and text QA benchmarks demonstrate substantial improvements over existing RAG baselines in accuracy, coverage, and traceability, establishing self-evolving knowledge graphs as a fundamental paradigm across modalities.
arXiv:2605.12279v2 Announce Type: replace-cross
Abstract: Let $fvs(G)$ denote the size of a minimum feedback vertex set of a digraph $G$. We study $fvs_g(n)$, which is the maximum $fvs(G)$ over all $n$-vertex planar digraphs $G$ of digirth $g$. We prove a planar-digraph analogue of the celebrated Lucchesi-Younger theorem showing that the minimum feedback vertex set is at most the maximum packing of a special type of directed cycles. As a corollary, we derive that $fvs_g(n)\le \frac{n-2}{g-2}$ for all $g\geq 3$. This improves all previously known upper bounds for $g \ge 4$, and for $g \ge 6$ it supersedes the best known upper bound of $\frac{2n-6}{g}$ (Esperet, Lemoine and Maffray, 2017) by a factor of 2.
On the other hand, we develop a new framework to construct planar digraphs of fixed digirth and large $fvs$. Using it, for $g = 6$ and every $g \ge 8$, we construct an infinite family of planar digraphs of digirth $g$ and $fvs(G) = \frac{g+2}{g^2} n + O(1)$. For $g= 7$, our construction gives $fvs(G) = \frac{2}{11} n + O(1)$ and for $g = 4$ and $5$, $fvs(G) = \frac{n}{g-1}$. These improve the best known lower bound of $\frac{n-1}{g-1}$ (Knauer, Valicov and Wenger, 2017) for all $g \ge 4$.
We thus obtain the two-sided bound $\frac{g+2}{g^2} \le \sup_{n \ge 1} \frac{fvs_g(n)}{n} \le \frac{1}{g-2}$ for all values $g = 6$ and every $g \ge 8$. The gap between the lower and the upper bound for $\sup_{n \ge 1} \frac{fvs_g(n)}{n}$ decreases from $\frac{g-2}{g(g-1)}$ to $\frac{4}{g^2(g-2)}$.
arXiv:2607.12786v1 Announce Type: new
Abstract: Cross-image comparative reasoning remains challenging for vision-language models (VLMs), especially when correct prediction requires fine-grained attribute grounding and globally consistent reasoning. We present CoRe, a unified framework for this problem. CoRe includes: (i) CoRe-20K, a large-scale triplet-based training set automatically constructed from structured visual metadata through a multi-expert collaborative pipeline, covering counting, depth, distance, and spatial relations; (ii) TriSR, a structured reward framework that jointly supervises attribute grounding, judgment alignment, and triplet consistency under GRPO optimization; and (iii) CoRe-Bench, the first benchmark dedicated to fine-grained cross-image comparative reasoning. Experiments show that CoRe substantially outperforms existing VLMs on CoRe-Bench while remaining competitive on standard multimodal benchmarks, achieving a 28.2-point gain in partial accuracy over the strongest baseline.
arXiv:2607.11949v1 Announce Type: cross
Abstract: We present a clinically deployed end-to-end auto-contouring system for cervical cancer radiotherapy planning, anchored by the Boundary-Aware Transformer with Region-Aware Mamba (BAT-RM), a hybrid architecture that integrates Sobel-gated boundary attention, a linear-time, multi-directional Mamba module for long-range context, and a boundary-skeleton-guided fusion gate. This design achieves linear-time complexity for long-range context modeling, avoiding the quadratic cost of full spatial self-attention. The full pipeline spans multi-institutional data collection, rigorous inter-rater quality assurance, external validation in an independent cohort, and a web-based clinical interface natively compatible with Varian, RayStation, and Monaco. Against four baselines, BAT-RM achieves superior performance across seven anatomical classes, with statistically significant improvements in target volumes, including GTV and CTV, and in organs at risk such as the rectum and bladder. A prospective multi-center reader study involving 13 radiation oncologists demonstrated that AI assistance elevates junior oncologists' IoU from 0.899 to 0.965, approaching senior-level accuracy, while reducing contouring time by more than 80%. The system also reduced expert consultation rates and improved inter-reader consistency, reflecting gains in both efficiency and quality assurance. Following clinical deployment at a partner hospital, the system reduced patient wait times from days to hours without additional staffing, enabling same-day or next-day initiation of treatment for routine cases. BAT-RM demonstrates that a rigorous research pipeline, from data curation to clinical deployment, can translate directly into measurable patient benefit in resource-constrained settings where the demand for radiotherapy far exceeds specialist capacity.
arXiv:2607.11955v1 Announce Type: cross
Abstract: Low-altitude uncrewed aerial vehicles (UAVs) can pose growing risks to airspace safety, security, and privacy. Cellular infrastructure can passively sense them without dedicated radar hardware by exploiting integrated sensing and communication (ISAC) technology. Most prior work exploits monostatic sensing or bistatic/multistatic configurations based on downlink measurements. To the best of our knowledge, this paper presents the first uplink framework, where multiple user equipments (UEs) transmit sounding reference signal (SRS) pilots and the base station (BS) receives the UAV-scattered echoes. Sensing from uplink SRS, however, introduces new challenges. Each UE has its own oscillator and timing loop, so the channel estimate at the BS carries residual timing, frequency, and amplitude impairments that corrupt the UAV delay and Doppler. Moreover, the UAV echo is weaker than both the line-of-sight (LOS) path and urban clutter, so detection from a single UE transmission is not reliable. We address these challenges by designing a LOS-referenced synchronization scheme and a joint detector. The synchronization reuses the existing timing advance (TA) command and an adjacent-occasion conjugate product to remove the residuals without additional signaling. Then the detector searches a shared 3D state space and accumulates evidence across UEs. It leverages a normalized contrast that exploits the bistatic geometry. We evaluate the framework in a cluttered urban scene at frequency range 1 (FR1) with four pedestrian UEs and a 100 MHz 5G New Radio (NR) waveform. The proposed pipeline achieves sub-nanosecond synchronization and a 4.84 m median 3D position error.
arXiv:2607.12093v1 Announce Type: cross
Abstract: Harvesting -- the periodic removal of individuals above or below a threshold trait value -- reshapes heterogeneous populations without altering their underlying stochastic dynamics. We study how repeated harvesting events steer the evolution of probability densities for classes of stochastic processes exhibiting both normal and anomalous dynamics, as well as a prototypical predator-prey model. Removal of the upper portion of the density drives the system to a quasi-steady state when viewed at the ``harvesting clock''. This state depends only on the harvesting threshold and frequency but not on the initial conditions. Removal of the lower portion of the density fixes its shape while generating a constant effective drift that exceeds that of the unharvested mean. Our results suggest the possibility of manipulating the dynamics of stochastic populations through external selection interventions.
arXiv:2607.12792v1 Announce Type: new
Abstract: Jailbreak-robustness research typically evaluates safety through generated responses using an LLM-as-judge approach. Such evaluations, however, are sensitive to the benchmark's grading procedure and capture only observed behavior on a given set of attacks, without directly revealing the hidden fragility of the underlying safety mechanisms. This work proposes JADR (Jacobian Assessment of Danger Recognition), a protocol that measures a model's internal representation through Jacobian space (J-space, a recently proposed workspace of verbalizable concepts) before the first response token is generated. For every prompt and layer we record the top-k J-space tokens; these are grouped into six behavioral scenario axes and compared between a danger sample based on StrongREJECT and a safe control drawn from XSTest and OKTest. The method does not call on an external judge model: the computation runs entirely locally, on the activations of the model under evaluation, which lets us compare both different models against each other and modifications of a single model -- quantization and fine-tuning in particular -- on the same terms. The final comparison rests on the proposed SafetyAUC metric, complemented with bootstrap confidence intervals. The protocol is applied to six models (Qwen3-1.7B, Qwen3-4B, Qwen3-8B, Qwen3-Uncensored-4B, Qwen3-SafeRL-4B, Gemma 2 9B) across three weight-representation regimes -- BF16, INT8, and INT4 -- and checked against an independent behavioral evaluation with the StrongREJECT grader. The metric separates models with a strong versus a weak internal safety mechanism with statistical significance and captures substantively different effects across quantization regimes.
arXiv:2607.12026v1 Announce Type: cross
Abstract: Finite groups are rigid algebraic objects, whose Cayley graphs expose a rich network geometry through which group-theoretic structure can be measured, compared, and learned. In this paper, a dataset of $131{,}406$ Cayley graphs is constructed, covering all groups of order at most $767$ except order $512$, recording exact algebraic labels for group properties together with a broad collection of graph, cycle, distance, and spectral statistics. This census aims to provide novel benchmarks for studying how finite-group properties are reflected in Cayley graph observables. It also yields new enumerative contributions: alongside recovering known OEIS sequences for standard group classes, new sequences for monolithic groups and for groups generated by at most three, four, and five elements are contributed to the OEIS. The accompanying network analysis identifies several empirical regularities and formulates testable conjectures, including relationships involving square clustering, Cayley graph diameter, average graph disorder, and spectral eigengaps of nilpotent groups. Finally, a comparison between classical models, an MLP, and graph neural network architectures is performed for predicting algebraic group properties directly from Cayley graph data. The results show that engineered graph statistics are highly informative, while GNNs, especially GIN and in some fixed-order settings GCN, can recover substantial structural signal directly from the graph. Such that graph-aware architectures show phases of optimality on these group-theoretic graph representations.
arXiv:2607.12774v1 Announce Type: new
Abstract: This article presents our results for the 11th Affective Behavior Analysis in-the-Wild (ABAW) competition. For multi-task learning with simultaneous prediction of valence, arousal, facial expressions, and action units on s-Aff-Wild2 dataset, we use frozen lightweight facial extractors, MT-EmotiDDAMFN and MT-EmotiEffNet-B0, with separate heads and systematic post-processing: temporal Gaussian smoothing, per-class expression bias, AffectNet blending, per-AU threshold tuning, and weighted backbone fusion. On the official validation set, our ensemble significantly exceeds the performance of the ConvNeXt baseline. For ambivalence/hesitancy video recognition on the expanded BAH dataset, we extend the audiovisual pipeline to video-level Macro F1 by late fusion of face, HuBERT audio, and RoBERTa text classifiers, temporal aggregation, and a global-text gate. Frame-level Weighted F1 on validation set rises from 0.74 in ABAW-8 to 0.79, while the best public-test video-level Macro F1 reaches 0.73. In both tasks, competitive performance is achieved without fine-tuning heavy backbones. These results indicate that systematic prediction calibration and lightweight multimodal fusion can rival substantially heavier end-to-end approaches while offering improved efficiency and deployment flexibility.
arXiv:2607.12782v1 Announce Type: new
Abstract: Hyperspectral foundation models learn transferable spectral-spatial representations from large-scale unlabeled data. They provide an effective paradigm for adapting to downstream hyperspectral image (HSI) classification tasks with limited labeled samples. However, spectral band configurations vary substantially across sensors, which makes direct model transfer difficult. Existing adaptation strategies often compress, select, or reshape the original spectra to match model-specific input requirements. These operations may discard useful spectral information and weaken local spectral continuity. To address this problem, we propose MBTI, a Multi-Branch efficient fine-tuning framework for Hyperspectral Image classification. MBTI adapts hyperspectral foundation models to downstream classification tasks while preserving full-band spectral information. First, we introduce a spectral-continuity-preserving multi-branch preprocessing strategy. The original HSI is divided into multiple continuous spectral subsets, and a band reuse mechanism is used when the remaining bands cannot form a complete branch. This avoids invalid padding and unnecessary spectral loss. Second, independent Low-Rank Adaptation (LoRA) modules are inserted into each branch. They enable different spectral intervals to learn task-specific discriminative features while keeping most pre-trained parameters frozen. Finally, a multi-branch channel attention fusion module adaptively recalibrates and integrates features from all spectral branches. Experiments on three public hyperspectral datasets show that MBTI achieves competitive and superior performance compared with representative classification methods. Under the final rank-8 configuration, only about 2.33\%--2.36\% of the parameters are trainable. The code will be available at https://github.com/Azhenmiddleblock/MBTI/tree/main.
arXiv:2607.12784v1 Announce Type: new
Abstract: Reinforcement Learning has revolutionized the landscape of robotic research, allowing robust learning of complex robotic skills in simulation. However, real-world deployment in open-ended environments requires strong safety guarantees to prevent dangerous or harmful behaviors. Safe Reinforcement Learning methods address this requirement by enforcing safety constraints. Nevertheless, learning under constraints often reduces learning speed and could lead to suboptimal task performance, as the agent must solve a more complex constrained optimization problem compared to unconstrained settings. To tackle this issue, in this work, we propose an extension of the ATACOM framework, a state-of-the-art reliable safety layer that can be integrated with existing Reinforcement Learning algorithms to enforce constraints derived from prior knowledge of the system or learned directly from data. Our proposed method, named ATACOM Directional Constraints (ATACOM-DC), significantly improves the safety-performance trade-off by introducing directional constraints that distinguish between actions approaching and moving away from constraint boundaries, activating constraint enforcement only when necessary. We evaluate our method across a range of challenging robotic control tasks in simulation, analyzing both constraint-violation costs and achieved task performance. Code and additional material at https://atacom-dc.robot-learning.net.
arXiv:2607.12787v1 Announce Type: new
Abstract: Recent advances in multimodal large language models (MLLMs) have significantly improved the performance of multimodal emotion recognition (MER) and enabled interpretable description generation by jointly modeling video, audio, and language, etc. However, these performance improvements are often accompanied by an increase in model parameter size (e.g, at least 7B), which simultaneously incurs high computational costs and reduces inference efficiency, thereby hindering real-time deployment on resource-constrained platforms such as robots and mobile devices. This raises a fundamental question: do we really need the multimodal MER model larger than 1B parameters for high-quality MER?
In this paper, we challenge the assumption that larger models are inherently necessary and proposes a lightweight MER framework (called Light-MER), which achieves better and faster multimodal sentiment understanding and recognition through knowledge distillation. It can transfer knowledge from a strong, large-scale teacher model to a lightweight sub-billion-parameter student model, aiming to preserve rich multimodal emotion reasoning and recognition while substantially improving deployment efficiency. Specifically, we introduce two new optimization strategies to enhance knowledge transfer: (1) a new optimal transport loss that combines Sliced Wasserstein Distance with hidden-state alignment, and (2) a new multi-reward optimization strategy based on GRPO that balances MER performance and efficiency, aimed at further enhancing the learning capabilities of student models. Extensive experiments on nine benchmark datasets demonstrate that Light-MER achieves state-of-the-art performance while significantly improving inference efficiency. This highlights the strong potential of small multimodal emotion language models for future research. Code is available at https://github.com/GAIR-Lab/Light-MER.
arXiv:2607.12788v1 Announce Type: new
Abstract: 3D integration packs more power into a smaller footprint, so a candidate design's actual throughput depends on its layout: which macro sits on which tier, where the hot spot lands, and how cache geometry maps to access cycles. Architectural simulators like gem5 report IPC under idealized timing. They do not produce the per-block power map, the cache cycle counts, or the 3D layout that decide the realized billion-instructions-per-second (BIPS), so early-stage 3D-IC exploration selects designs without accounting for the effects that decide whether they throttle on silicon. We present CLIP-3D, a shift-left flow that exposes 3D layout-driven thermal, wire, and cache effects to early-stage architectural exploration before any sign-off tool is invoked. The first stage lifts an architectural configuration into a physical block representation: McPAT for per-block dynamic and leakage power, CACTI for cache geometry and access cycles, and a HotSpot-compatible 3D stack discretization. The second stage runs an analytical 3D thermal-aware floorplanner over that representation. The floorplanner objective embeds a closed-form sustained-frequency expression derived from the linearity of HotSpot's steady-state operator and the standard CMOS power-frequency decomposition. Cross-tier macro assignment and in-plane placement are co-optimized for the realized BIPS rather than for a half-perimeter wirelength (HPWL)-plus-temperature surrogate with hand-tuned weights.
arXiv:2607.12911v1 Announce Type: new
Abstract: Multimodal Large Language Models (MLLMs) are increasingly used for dietary assessment from meal images, where retrieval-augmented grounding was shown to sharpen nutrition estimates. However, we find this premise no longer holds for current MLLMs. A modern MLLM's direct estimate now matches or surpasses the full retrieval pipeline. This raises a question: if retrieval no longer improves the overall estimate, can it still deliver the two things clinicians value, accurate portions and a traceable, item-by-item record? We pursue this while preserving what matters for clinical adoption: minimal user burden (a single, unannotated meal image), explainability (an auditable record), and privacy (locally hosted inference). We introduce Open-KNEAD, a knowledge-grounded agentic framework for meal nutrition estimation that is training-free and locally deployable. Each decomposed food item is grounded to a Food and Nutrient Database for Dietary Studies (FNDDS) code via selective, nutrient-aware retrieval, composing an auditable per-item record. Across two open MLLM families and three cuisines, Open-KNEAD improves portion estimates over both prior grounding methods and direct estimation in most backbone-dataset settings. An agent-internal recipe-prior step further recovers the invisible cooking-added energy that biases estimates on non-US cuisine. The advantage is largest on the dietitian-verified ACETADA dataset, where the local open agent surpasses the direct portion estimates of two frontier closed models by roughly $30\%$ and $53\%$, all while keeping every meal image on local hardware. We release the Open-KNEAD framework and its agent-ready FNDDS knowledge base.
arXiv:2607.12789v1 Announce Type: new
Abstract: The $\mathcal{O}(N^2)$ complexity of attention over $N$ tokens remains a computational bottleneck in transformer models. Vector-Quantized (VQ) attention reduces this to $\mathcal{O}(MN)$ by representing keys with $M$ codewords, but applies uniform codebook capacity regardless of where attention mass concentrates: high-attention regions of key space may be coarsely approximated while low-attention regions waste representational capacity. We propose Adaptive Vector-Quantized (AVQ) Attention, which adaptively allocates codebook capacity based on attention importance. Starting from a small set of codewords, our method identifies the most important codes during the forward pass and refines them with pre-learned child codewords, achieving fine-grained quantization where it matters most while maintaining coarse quantization elsewhere. We develop an implementation using custom Triton kernels that enables the full adaptive refinement process, including importance scoring, child codeword insertion, and parent contribution replacement, to be carried out within the tiled computation paradigm of Flash Attention with minimal overhead. Our approach maintains $\mathcal{O}(MN)$ complexity while achieving improved accuracy-efficiency trade-offs compared to fixed-codebook VQ-attention.
arXiv:2607.12189v1 Announce Type: cross
Abstract: We prove new necessary and sufficient conditions for uniform asymptotic stability under arbitrary switching of two-dimensional switched homogeneous systems with a finite number of subsystems using a worst-case switching analysis. The novelty of our approach is in its explicit nature, which allows us to then study in detail the codimension-one bifurcations of stability of the origin in switched linear systems and further conclude new local and global stability results for certain classes of nonlinear switched systems. In particular, we formulate an analogue of Lyapunov's indirect method for $\mathcal{C}^{1}$ switched nonlinear systems and derive a new method for determining the existence of a bounded basin of attraction for a class of switched nonlinear systems.
arXiv:2607.12155v1 Announce Type: cross
Abstract: We introduce fkcompute, an open-source package for computing the Gukov--Manolescu invariant of links from a braid presentation. fkcompute implements Park's inverted state sum through a three-phase pipeline. First, a search is performed for a suitable braid presentation and for an additional inversion data on the braid. Then, the state space of the inverted sum is encoded as a polytope, bounded by the associated linear constraint system. Finally, the invariant is constructed by multiplication of R-matrices associated to the states. Benchmarks show that prime knots up to 12 crossings, and prime links up to 10 crossings and of at most 3 components, are comfortably within reach. As a result, fkcompute is used to compile the first public database of the Gukov--Manolescu invariant. The package is available as a Python library, a command-line tool, and a Mathematica paclet.
arXiv:2603.08503v2 Announce Type: replace
Abstract: Omnidirectional images are increasingly used in robotics and vision due to their wide field of view. However, extending 3D Gaussian Splatting (3DGS) to panoramic camera models remains challenging, as existing formulations are designed for perspective projections and naive adaptations often introduce distortion and geometric inconsistencies. We present Spherical-GOF, an omnidirectional Gaussian rendering framework built upon Gaussian Opacity Fields (GOF). Unlike projection-based rasterization, Spherical-GOF performs GOF ray sampling directly on the unit sphere in spherical ray space, enabling consistent ray-Gaussian interactions for panoramic rendering. To make the spherical ray casting efficient and robust, we derive a conservative spherical bounding rule for fast ray-Gaussian culling and introduce a spherical filtering scheme that adapts Gaussian footprints to distortion-varying panoramic pixel sampling. Extensive experiments on standard panoramic benchmarks (OmniBlender and OmniPhotos) demonstrate competitive photometric quality and substantially improved geometric consistency. Compared with the strongest baseline, Spherical-GOF reduces depth reprojection error by 57% and improves cycle inlier ratio by 21%. Qualitative results show cleaner depth and more coherent normal maps, with strong robustness to global panorama rotations. We further validate generalization on OmniRob, a real-world robotic omnidirectional dataset introduced in this work, featuring UAV and quadruped platforms. The source code and the OmniRob dataset will be released at https://github.com/1170632760/Spherical-GOF.
arXiv:2603.28583v2 Announce Type: replace
Abstract: Despite the success of Vision-Language Models (VLMs), misleading charts remain a significant challenge due to their deceptive visual structures and distorted data representations. We present ChartCynics, an agentic dual-path framework designed to unmask visual deception via a "skeptical" reasoning paradigm. Unlike holistic models, ChartCynics decouples perception from verification: a Diagnostic Vision Path captures structural anomalies (e.g., inverted axes) through strategic ROI cropping, while an OCR-Driven Data Path ensures numerical grounding. To resolve cross-modal conflicts, we introduce an Agentic Summarizer optimized via a two-stage protocol: Oracle-Informed SFT for reasoning distillation and Deception-Aware GRPO for adversarial alignment. This pipeline effectively penalizes visual traps and enforces logical consistency. Evaluations on two benchmarks show that ChartCynics achieves 74.43% and 64.55% accuracy, providing an absolute performance boost of ~29% over the Qwen3-VL-8B backbone, outperforming state-of-the-art proprietary models. Our results demonstrate that specialized agentic workflows can grant smaller open-source models superior robustness, establishing a new foundation for trustworthy chart interpretation.
arXiv:2602.09907v2 Announce Type: replace
Abstract: College students increasingly use AI chatbots to support academic reading, yet we lack granular understanding of how these interactions shape their reading experience and cognitive engagement. We conducted an eight-week longitudinal study with 15 undergraduates who used AI to support assigned readings in a course. We collected 838 prompts across 239 reading sessions and developed a coding schema categorizing prompts into four cognitive themes: Decoding, Comprehension, Reasoning, and Metacognition. Comprehension prompts dominated (59.6%), with Reasoning (29.8%), Metacognition (8.5%), and Decoding (2.1%) less frequent. Most sessions (72%) contained exactly three prompts, the required minimum of the reading assignment. Within sessions, students showed natural cognitive progression from comprehension toward reasoning, but this progression was truncated. Across eight weeks, students' engagement patterns remained stable, with substantial individual differences persisting throughout. Qualitative analysis revealed an intention-behavior gap: students recognized that effective prompting required effort but rarely applied this knowledge, with efficiency emerging as the primary driver. Students also strategically triaged their engagement based on interest and academic pressures, exhibiting a novel pattern of reading through AI rather than with it: using AI-generated summaries as primary material to filter which sections merited deeper attention. We discuss design implications for AI reading systems that scaffold sustained cognitive engagement.
arXiv:2604.19632v2 Announce Type: replace
Abstract: Graphic design images consist of multiple editable layers, such as text, background, and decorative elements, while most generative models produce rasterized outputs without explicit layer structures, limiting downstream editing. Existing graphic design parsing methods typically rely on multi-stage pipelines combining layout prediction, matting, and inpainting, which suffer from error accumulation and limited controllability. We propose a hybrid generative framework for raster-to-layer graphic design parsing that decomposes a design image into editable text, background, and sticker layers. Text regions are parsed using a vision-language model into a text rendering protocol, enabling faithful reconstruction and flexible re-editing, while background and sticker layers are generated using a multi-branch diffusion architecture with RGBA support. We further introduce ParserReward and integrate it with Group Relative Policy Optimization to align generation quality with human design preferences. Extensive experiments on two challenging datasets, \emph{i.e.,} the Parser-40K and Crello datasets, demonstrate superior performance over existing methods, \emph{eg.,} achieving an overall average improvement of 23.7\% across all metrics.
arXiv:2606.25431v2 Announce Type: replace
Abstract: We study algorithmic fair contract design, where a principal designs task-level contracts and fairly delegates a set of tasks to a set of agents. Prior work reveals a fairness-revenue dilemma: exact envy-free (EF) contracts may have an unbounded price of fairness (PoF), while approximate notions avoid this unboundedness only by weakening strict fairness. To address this dilemma, we propose a novel scheme, called {\it Envy-free Contracts with Subsidies} (EFS), in which the principal may additionally offer agent-specific subsidies to restore strict fairness. Our main technical result is a tight characterization of the price of fairness for EFS contracts. In sharp contrast to EF contracts, whose PoF can be unbounded, we show that the PoF of EFS contracts is $n^{n+O(1)}$, where $n$ is the number of agents. Moreover, EFS contracts can outperform EF contracts by an arbitrarily large factor in terms of the principal's revenue. Finally, we present the complexity landscape: computing optimal EFS contracts is NP-hard in general, whereas a polynomial-time algorithm exists when the number of tasks is constant.
arXiv:2602.16180v2 Announce Type: replace
Abstract: Photochromic materials enable dynamic optical modulation through reversible transitions between distinct absorption states, with broad potential for smart windows, adaptive optics, and reconfigurable photonic devices. Micron-scale photochromic hybrid films present a particularly attractive platform for these applications, combining straightforward preparation with substantial optical modulation and scalability for high-volume fabrication. However, rational design of such films remains fundamentally constrained by the absence of well-defined optical constants. Unlike homogeneous thin films, micron-scale hybrid photochromic materials comprise active particles dispersed non-uniformly within polymer matrices. Conventional first-principles electromagnetic simulations face substantial computational costs and discrepancies between simulated and experimental particle distributions. Here, we introduce a data-driven framework that extracts effective optical constants directly from minimal experimental transmittance measurements. Our dual-state effective model approximates the complex inhomogeneous photochromic layer as a compressed homogeneous medium characterized by pseudo-refractive indices and pseudo-extinction coefficients for both pristine and UV-irradiated states. Through systematic optimization against experimental data from tungsten oxide-polyvinylpyrrolidone hybrid films, we determine wavelength-dependent pseudo-optical constants and compression ratios that enable accurate prediction of optical modulation within the tested thickness range. Our methodology establishes a framework for engineering hybrid photochromic systems and demonstrates how data-driven modeling can overcome limitations in characterizing complex nanostructured materials.