arXiv:2607.10605v1 Announce Type: new
Abstract: In recent years, Unmanned Aerial Vehicles (UAVs) or drones have gained rapid response in terms of security, search and rescue (SAR), border surveillance, etc. Existing monitoring frameworks often struggle to maintain detection consistency when targets undergo significant scale variations due to altitude changes, leading to critical information gaps. To address this issue, this work proposes an integrated real-time detection pipeline for detecting targets through the wireless live drone video feed. Build upon YOLOv8-nano architecture, extensive flight experiments were conducted to determine the detection performance across multiple flight altitudes. Trained on VisDrone2019 dataset, the results of YOLOv8-nano model achieves 57.4%, 41%, 44.8% and 20.3% in precision, recall, mAP and mAP50:95 respectively. While demonstrating on real environment, this analysis revealed that the algorithm achieves near-total detection reliability at altitudes between 16 and 25 meters with the detection frame rate consistently maintained above 41 FPS and reaching a peak of 50 FPS. However, the goal of this work is to enable real-time person detection from an aerial platform via wireless transmission. This approach effectively addresses the dual challenges of identifying targets at varying scales and ensuring near-to-accurate localization during aerial observation.
Science Journals
arXiv:2607.10797v1 Announce Type: new
Abstract: Assembly action understanding is a key enabler for effective human-robot collaborative assembly, yet it remains challenging due to subtle motions and fine-grained hand-object interactions. We adapt vision-language models (VLMs) to this challenging domain with Compositional Context Fine-Tuning (CCFT), a method that decomposes assembly actions into semantic elements (Verb, Object, Tool) and fine-tunes VLMs to recognize each action element using templated question-answering pairs. This approach ensures near-deterministic outputs. To enable efficient and effective multi-task learning under limited data, a Layer-Partitioned Alternating Training (LP-AT) method is presented, which assigns distinct model layers to recognize specific action elements through element-specific low-rank adapters. LP-AT alternates weight updates across element-specific adapters, reducing cross-task interference while enabling per-adapter hyperparameter optimization. Furthermore, we create HA-ViD-VQA and IKEA-ASM-VQA datasets from existing assembly video datasets. Extensive experiments on these datasets demonstrate that our method consistently outperforms strong action recognition baselines while providing interpretable element-level predictions that can support diverse downstream applications.
arXiv:2607.11118v1 Announce Type: new
Abstract: Transparent objects pose a fundamental challenge for depth estimation and 3D reconstruction due to their violation of Lambertian assumptions, leading to severe geometry degradation in downstream tasks. To address this, we propose a novel geometry-guided preprocessing framework \textbf{GHOST} that leverages visual foundation models to transform transparent regions into opaque, structurally consistent representations without requiring downstream model retraining. Specifically, our pipeline utilizes (1) \textbf{TransDINO} and (2) \textbf{TransDecomp} to disentangle masks and transparency physical properties, while (3) \textbf{DAF-Net} recovers surface normal priors to encode geometric curvature. Subsequently, (4) \textbf{GeoSemTransNet} integrates these multi-modal cues to synthesize a texture-rich opaque RGB image that preserves the transparent object's 3D structure. Extensive experiments demonstrate that our method significantly enhances the accuracy of state-of-the-art depth estimation and reconstruction models on transparent objects by restoring essential photometric cues.
arXiv:2607.10910v1 Announce Type: new
Abstract: We present ZoRRO (Zero-Weight Personalized Recommender System), a zero-weight, training-free framework for personalized news recommendation designed for scalable real-world deployment. ZoRRO outperforms strong neural baselines in offline ranking evaluations and achieves click-through rate performance in online A/B testing that is nearly on par with a state-of-the-art deep learning model, while operating more than 600 times faster. Our experiments reveal gaps between offline and online performance and demonstrate that models with similar click-through rate outcomes can produce markedly different recommendation distributions, thereby influencing the overall news flow. These findings position ZoRRO as a practical and efficient solution for large-scale news recommendation and highlight the importance of evaluating recommender systems using metrics beyond accuracy alone.
arXiv:2607.11575v1 Announce Type: new
Abstract: We propose a new strategy for gradient-based unconstrained optimization, involving two parallel sequences of iterates that cooperate to determine their stepsizes via a \textit{Twin-Step} principle. Rather than minimizing the objective function individually, the algorithm selects steplengths that minimize the Euclidean distance between the two gradient based processes occurring simultaneously at each iteration. The theoretical analysis shows that the convergence of the mutual distance is governed by the angle between the search directions. In particular the effectiveness of the overall process degrades as the directions approach parallelism. To ensure robustness against collinearity, we introduce a hybrid framework, Twin-ABB$_{\min}$, which switches to the Adaptive Barzilai--Borwein method when the geometric cooperation becomes ineffective. Extensive and very promising numerical results evidence that the Twin phase creates favorable initial conditions for subsequent BB-type iterations.
arXiv:2607.09707v1 Announce Type: new
Abstract: An earlier work that replaced the de Sitter-Schwarzschild metric for a cosmological constant Lambda <=0 by an effective anti-de Sitter black hole analytic at Lambda = 0 is here extended to the horizon structure through its three possible roots. We replace the de Sitter-Schwarzschild metric for all possible values of Lambda and the Schwarzschild radius R for the three possible available roots by either a Schwarzschild black hole whose radius depends on both R and Lambda or a de Sitter space whose cosmological constant depends on both R and Lambda.
arXiv:2607.10288v1 Announce Type: new
Abstract: Autonomous navigation in dense and highly dynamic environments requires both physically feasible control and low-latency replanning. Optimization-based methods such as Model Predictive Control (MPC) explicitly handle robot kinematics and safety constraints, but repeated nonlinear optimization can limit real-time responsiveness. Deterministic behavior-cloning policies enable efficient inference but may fail to represent multimodal avoidance behaviors, whereas diffusion policies capture multimodality at the cost of time-consuming iterative denoising. We propose PIER-Flow (Physics-Informed Efficient Rectified Flow), a lightweight navigation policy for mobile robots. By distilling an MPC expert into a continuous-time Ordinary Differential Equation (ODE), PIER-Flow achieves single-step action generation through parallel latent sampling and lightweight feasibility selection. We introduce a physics-informed training objective to enforce kinematic consistency, paired with an asynchronous action chunking architecture for robust sim-to-real deployment. Extensive simulations demonstrate that PIER-Flow achieves a 98.85\% success rate and zero collisions, with an average inference of $\sim$1.29 ms, which accelerates planning by 37.2$\times$ compared to MPC and over 800$\times$ against standard diffusion models. Crucially, real-world deployment on a resource-constrained edge computer further achieves an approximately stable inference latency of $\sim$5.3 ms, avoiding the latency spikes and freezing events observed with planning baselines.
arXiv:2602.18757v3 Announce Type: replace
Abstract: Human driving behavior is inherently diverse, yet most end-to-end autonomous driving (E2E-AD) systems learn a single average driving style, neglecting individual differences. Achieving personalized E2E-AD faces challenges across three levels: limited real-world datasets with individual-level annotations, a lack of quantitative metrics for evaluating personal driving styles, and the absence of algorithms that can learn stylized representations from users' trajectories. To address these gaps, we propose Person2Drive, a comprehensive personalized E2E-AD platform and benchmark. It includes an open-source, flexible data collection system that simulates realistic scenarios to generate scalable, diverse personalized driving datasets; style vector-based evaluation metrics with Maximum Mean Discrepancy and KL divergence to comprehensively quantify individual driving behaviors; and a personalized E2E-AD framework with a style reward model that efficiently adapts E2E models for safe and individualized driving. Crucially, our framework enables plug-and-play personalization by fine-tuning only the trajectory prediction head, preserving the pretrained base model and ensuring safety. Extensive experiments demonstrate that Person2Drive enables fine-grained analysis and effective personalization, while preserving driving performance and success rate even in challenging scenarios.
arXiv:2602.19598v2 Announce Type: replace
Abstract: Eye-tracking-while-reading corpora are a valuable resource for many different disciplines and use cases. Use cases range from studying the cognitive processes underlying reading to machine-learning-based applications, such as gaze-based assessments of reading comprehension. The past decades have seen an increase in the number and size of eye-tracking-while-reading datasets as well as increasing diversity with regard to the stimulus languages covered, the linguistic background of the participants, or accompanying psychometric or demographic data. The spread of data across different disciplines and the lack of data sharing standards across the communities lead to many existing datasets that cannot be easily reused due to a lack of interoperability. In this work, we aim at creating more transparency and clarity with regards to existing datasets and their features across different disciplines by i) presenting an extensive overview of existing datasets, ii) simplifying the sharing of newly created datasets by publishing a living overview online, https://t.uzh.ch/1Yh, presenting over 55 features for each dataset, and iii) integrating all publicly available datasets into the Python package pymovements which offers an eye-tracking datasets library. By doing so, we aim to strengthen the FAIR principles in eye-tracking-while-reading research and promote good scientific practices, such as reproducing and replicating studies.
arXiv:2602.19951v2 Announce Type: replace
Abstract: Metaprogramming enables the generation of performant code, while gradual typing facilitates the smooth migration from untyped scripts to robust statically typed programs. However, combining these features with imperative state - specifically mutable references - introduces the classic peril of scope extrusion, where code fragments containing free variables escape their defining lexical context. While static type systems have employed environment classifiers to successfully tamed this interaction, enforcing these invariants in a gradual language remains an open challenge.
This paper presents $\lambda^{\alpha,\star}_{\text{Ref}}$, the first gradual metaprogramming language that supports mutable references while guaranteeing scope safety. To put $\lambda^{\alpha,\star}_{\text{Ref}}$ on a firm foundation, we also develop its statically typed sister language, $\lambda^{\alpha}_{\text{Ref}}$, which introduces unrestricted subtyping for environment classifiers. We mechanize the proof of scope safety for $\lambda^{\alpha,\star}_{\text{Ref}}$, contributing the first mechanized proof of scope safety for a statically typed language. Our key innovation, however, is the dynamic enforcement of the environment classifier discipline in $\lambda^{\alpha,\star}_{\text{Ref}}$, enabling the language to mediate between statically verified scopes and dynamically verified scopes. The dynamic enforcement is carried out in a novel cast calculus $\mathrm{CC}^{\alpha,\star}_{\text{Ref}}$ that uses an extension of Henglein's Coercion Calculus to handle code types, classifier polymorphism, and subtype constraints. We prove that $\lambda^{\alpha,\star}_{\text{Ref}}$ satisfies type safety and scope safety. Finally, we provide a space-efficient implementation strategy for the dynamic scope checks, ensuring that the runtime overhead remains practical. All of our results are fully mechanized in Agda.
arXiv:2602.21247v3 Announce Type: replace
Abstract: The fastest indexes for Approximate Nearest Neighbor Search today are also the slowest to build: graph-based methods like HNSW and Vamana achieve state-of-the-art query performance but have large construction times due to relying on random-access-heavy beam searches. We introduce PiPNN (Pick-in-Partitions Nearest Neighbors), an ultra-scalable graph construction algorithm that avoids this ``search bottleneck'' that existing graph-based methods suffer from.
PiPNN's core innovation is HashPrune, a novel online pruning algorithm which dynamically maintains sparse collections of edges. HashPrune enables PiPNN to partition the dataset into overlapping sub-problems, efficiently perform bulk distance comparisons via dense matrix multiplication kernels, and stream a subset of the edges into HashPrune. HashPrune guarantees bounded memory during index construction which permits PiPNN to build higher quality indices without the use of extra intermediate memory.
PiPNN builds state-of-the-art indexes up to 11.6x faster than Vamana (DiskANN) and up to 12.9x faster than HNSW. PiPNN is significantly more scalable than recent algorithms for fast graph construction. PiPNN builds indexes at least 19.1x faster than MIRAGE and 17.3x than FastKCNA while producing indexes that achieve higher query throughput. PiPNN enables us to build, for the first time, high-quality ANN indexes on billion-scale datasets in under 20 minutes using a single multicore machine.
arXiv:2607.10117v1 Announce Type: new
Abstract: We propose a mechanism for the generation of intense ultrafast mid-infrared radiation from heavily doped semiconductors. An ultrafast optical pulse transfers a finite impulse to the free carriers, displacing the screening clouds surrounding ionized dopants and inducing coherent plasma-frequency oscillations of the resulting polarization. We derive an exact analytical solution for the corresponding nonequilibrium dynamics and the resulting far-field radiation emitted by a thin semiconductor film. For realistic parameters of heavily doped GaAs, the emitted mid-infrared pulses can reach electric-field amplitudes on the order of $10^7\,{\rm V/m}$ directly in the far field, without relying on optical focusing.
arXiv:2607.10296v1 Announce Type: new
Abstract: Reasoning failures in large language models (LLMs) are usually evaluated from final answers, but a wrong answer does not reveal why the model failed. The same incorrect output may reflect missing capability, an unstable reasoning trajectory, or a failure to activate a reasoning state that is already available in the frozen model. Existing prompting and benchmark-based evaluation methods mostly operate at the output level, while generic activation-steering methods typically apply global directions without diagnosing which examples require intervention. In this paper, we introduce SPARK, which uses hidden-state response to diagnose whether a model internally enters an effective reasoning state and to guide lightweight test-time steering. The key observation is that raw hidden-state susceptibility is strongly confounded by prompt length, especially in programmatic and algorithmic reasoning where harder serialized instances naturally become longer. SPARK therefore uses length-controlled susceptibility to separate input-scale effects from residual reasoning activation, and combines this signal with cross-layer coordination to select reasoning-active anchors and under-activated hard examples. We use FRONTIER-4.5K as a controlled programmatic reasoning suite for latent profiling and difficulty-aware analysis, and evaluate SPARK-Steering on GSM8K and MATH-500 with forward-only benchmark profiling. Our method improves Qwen3 series models consistently; on MATH-500, accuracy rises from 82.0% to 84.6% for Qwen3-4B and from 82.4% to 85.6% for Qwen3-8B. These results suggest that susceptibility can serve not only as a diagnostic signal for reasoning failures, but also as a practical guide for targeted test-time intervention.
arXiv:2607.10993v1 Announce Type: new
Abstract: Foundation models such as CLIP have enabled open-vocabulary object detectors that generalise to novel categories via vision-language similarity. However, the confidence scores these detectors produce are not reliable localization probability estimates: they conflate visual scale and semantic query specificity with the true detection signal. Through controlled experiments on COCO across three foundation-model-based detectors (GroundingDINO, OWL-ViT, YOLO-World), with the scale-bias finding further replicated on LVIS (1,203 categories) using GroundingDINO, we show that s=cos(v,t) is a biased mixture of two effects. Scale bias (alpha = +0.064, r = 0.579, p = 1.29 x 10^-58) systematically inflates scores for large objects. Semantic bias (beta = -0.705, p = 5.23 x 10^-41) suppresses scores for generic queries. Both biases are structurally inevitable from CLIP's image-level pretraining. Threshold adjustment cannot remove them: oracle per-scale thresholding yields Delta F1 = +0.001 for small objects versus +0.102 for large. A parameter-free temperature scaling correction improves small-object Recall@10 by 19.6% (p < 0.01) without retraining. This comes at a modest, measurable cost to pooled-ranking precision, so the bias is partially, not freely, reversible at inference time. These findings reveal a fundamental limitation of adapting image-level foundation models to region-level detection tasks.
arXiv:2602.21255v2 Announce Type: replace
Abstract: We establish a general equilibrium theory for systems of large language model (LLM) agents operating under centralized orchestration. The framework is a production economy in the sense of Arrow-Debreu (1954), extended to infinite-dimensional commodity spaces following Bewley (1972). Each LLM agent is modeled as a firm whose production set Y a $\subset$ H = L 2 ([0, T ], R R ) represents the feasible metric trajectories determined by its frozen model weights. The orchestrator is the consumer, choosing a routing policy over the agent DAG to maximize system welfare subject to a budget constraint evaluated at functional prices p $\in$ H A . These prices-elements of the Hilbert dual of the commodity space-assign a shadow value to each metric of each agent at each instant. We prove, via Brouwer's theorem applied to a finitedimensional approximation V K $\subset$ H, that every such economy admits at least one general equilibrium (p * , y * , $\pi$ * ). A functional Walras' law holds as a theorem: the value of functional excess demand is zero for all prices, as a consequence of the consumer's budget constraint-not by construction. We further establish Pareto optimality (First Welfare Theorem), decentralizability of Pareto optima (Second Welfare Theorem), and uniqueness with geometric convergence under a contraction condition (Banach). The orchestration dynamics constitute a Walrasian t{\^a}tonnement that converges globally under the contraction condition, unlike classical t{\^a}tonnement (Scarf, 1960). The framework admits a DSGE interpretation with SLO parameters as policy rates.
arXiv:2602.21312v4 Announce Type: replace
Abstract: This work considers a number of optimization problems and reductive relations between them. The two main problems we are interested in are the Optimal Decision Tree and Set Cover. We study these two fundamental tasks under precedence constraints, that is, if a test (or set) $X$ is a predecessor of $Y$, then in any feasible decision tree $X$ needs to be an ancestor of $Y$ (or respectively, if $Y$ is added to set cover, then so must be $X$). For the Optimal Decision Tree we consider two optimization criteria: worst case identification time (height of the tree) or the average identification time. Similarly, for the Set Cover we study two cost measures: the size of the cover or the average cover time.
Our approach is to develop a number of algorithmic reductions, where an approximation algorithm for one problem provides an approximation for another via a black-box usage of a procedure for the former. En route we introduce other optimization problems either to complete the `reduction landscape' or because they hold the essence of combinatorial structure of our problems. The latter is brought by a problem of finding a Maximum Density Precedence-Closed Subfamily, where the density is defined as the ratio of the number of items the family covers to its size. We provide $\mathcal{O}^*(\sqrt{m})$-approximation polynomial-time algorithms for all aforementioned problems. The picture is complemented by a number of hardness reductions that provide $\mathcal{O}(m^{1/12-\epsilon})$-inapproximability results for the decision tree and covering problems. Besides giving a complete set of results for general precedence constraints, we also provide polylogarithmic approximation guarantees for two most typically studied and applicable graph types, outforests and inforests. By providing corresponding hardness results, we show most of these results to be tight.
arXiv:2602.22599v2 Announce Type: replace
Abstract: We study with ab-initio theory high harmonic generation (HHG) from a series of gas-phase fullerenes (from C$_{20}$ to C$_{60}$, including isomers) under varying laser conditions (linearly polarized at various angles and different ellipticities). We explore the role of multiple orbitals in the dynamics and show that due to the tight energy level spacing in these systems (forming the equivalent of energy bands), multiple orbitals contribute and cause severe spectral interferences. HHG cutoff and plateau ranges are shown relatively similar across species of different sizes. We further explore the role of correlations, which are known to be prevalent in C$_{60}$ and similar species and responsible for plasmonic resonances. We find that the independent-particle approximation, where electrons are not dynamically interacting, fails to quantitatively describe features in the spectrum besides the cutoff energy. This failure is broad across the HHG plateau and perturbative regime in all species. Broadly, correlations are seen to reduce HHG yields and cause sharper emission peaks. Lastly, we study HHG ellipticity and angular dependence across species and show that: (i) HHG angular sensitivity becomes less prevalent for larger fullerenes. This arises from a more isotropic structure of the higher point-group molecules. (ii) HHG yields decay faster with the driving laser ellipticity for smaller systems, owing to their reduced size creating smaller recombination cross sections with re-colliding electron wave packets (with C$_{60}$ posing an anomalous exception to this rule). Our predictions pin-point fullerenes as an ideal system for exploring multi-electron interactions in HHG and strong-field physics, and should motivate experiments.
arXiv:2602.23565v2 Announce Type: replace
Abstract: In many economically relevant contexts where machine learning is deployed, multiple platforms obtain data from the same pool of users, each of whom selects the platform that best serves them. Prior work in this setting focuses exclusively on the "local" losses of learners on the distribution of data that they observe. We find that there exist instances where learners who use existing algorithms almost surely converge to models with arbitrarily poor global performance, even when models with low full-population loss exist. This happens through a feedback-induced mechanism, which we call the overspecialization trap: as learners optimize for users who already prefer them, they become less attractive to users outside this base, which further restricts the data they observe. Inspired by the recent use of knowledge distillation in modern ML, we propose an algorithm that allows learners to "probe" the predictions of peer models, enabling them to learn about users who do not select them. Our analysis characterizes when probing succeeds: this procedure converges almost surely to a stationary point with bounded full-population risk when probing sources are sufficiently informative, e.g., a known market leader or a majority of peers with good global performance. We verify our findings with semi-synthetic experiments on the MovieLens, Census, and Amazon Sentiment datasets.
arXiv:2602.23993v2 Announce Type: replace
Abstract: We present gradiend, an open-source Python package that operationalizes the GRADIEND method for learning feature directions from factual-counterfactual MLM and CLM gradients in language models. The package provides a unified workflow for feature-related data creation, training, evaluation, visualization, persistent model rewriting via controlled weight updates, and multi-feature comparison. We demonstrate gradiend through an English pronoun running example, a semantic sentiment use case that evaluates lexical generalization to held-out target words, and a large-scale feature comparison.
arXiv:2607.11044v1 Announce Type: new
Abstract: Humans can infer hidden physical processes from sparse observations, yet current evaluation protocols for Vision Language Models fail to assess whether such physical reasoning is genuinely captured. To address this gap, we introduce Retrospective Physical Process Reasoning, a new evaluation paradigm to reason backward from outcomes under explicit physical constraints. Building on the paradigm, we present RetroHolmes, the first real-world benchmark for Retrospective Physical Process Reasoning, comprising object-centric image pairs annotated with reachability labels and causal step sequences across diverse physical transitions. Using RetroHolmes, we analyze state of the art Vision Language Models and uncover systematic failure modes, including judgment bias in reachability assessment and belief dominance over physical evidence, mirroring sycophancy behavior observed in large language models. We further demonstrate a simple analysis-by-synthesis instantiation with visual simulation as an intermediate step, validating the diagnostic value of RetroHolmes and highlighting the importance of physically grounded intermediate representations for physical reasoning.
arXiv:2607.11046v1 Announce Type: new
Abstract: LLM-based agents are increasingly being used to support software development, yet their performance in repository-level tasks depends on retrieving the right code context. Existing studies have explored file-level localization using traditional information retrieval over file paths and raw source code. However, the role of textual code representations in retrieval and localization remains underexplored.
We study file-level bug localization as a representation-driven retrieval problem. Across the Long Code Arena (LCA) and SWE-bench Verified (SWE) datasets, we compare five code representations: file paths, raw source code, and three LLM-generated textual representations. Our experiments include lexical, semantic, and LLM-based retrieval, followed by LLM-based post-retrieval ranking. We quantify the cost incurred by a representation through the representation footprint. We find that the choice of code representation affects both localization effectiveness and cost. Role-aware summaries outperform file-path representations by up to 40% Hit@5 while requiring a representation footprint 10.4 to 20.9x smaller than raw source code. Combining complementary representation results and ranking retrieved candidates with an LLM provides further gains of up to 31.9% and 42.0%, respectively. Overall, role-aware summaries provide the best cost-effectiveness trade-off, while raw source code offers effectiveness in some settings at a significantly higher cost. A case study with Agentless reveals the utility of our techniques within a well-known pipeline, reaching 94% Hit@6 on file localization (+4.7% against the baseline). Our findings suggest that code representation should be treated as a first-class design choice in agentic localization pipelines, guided by pipeline stage and cost-accuracy requirements.
arXiv:2607.11153v1 Announce Type: new
Abstract: Content Addressable Memory (CAM) is an important memory paradigm, which performs fast search by comparing an input query against all stored entries in parallel, achieving $O(1)$ lookup complexity. CAM is typically built upon conventional memory technologies, such as SRAM and Non-Volatile Memory (NVM). Accordingly, CAM can also be subject to the reliability challenges of these underlying technologies. In traditional memory systems, protection codes play a critical role in ensuring reliability and have been extensively studied. However, protection codes for CAM have remained largely unexplored. This paper takes an initial step toward addressing this longstanding gap by introducing a non-traditional code design.
arXiv:2607.10629v1 Announce Type: new
Abstract: The Token Jumping and Sliding Token problems are fundamental reconfiguration problems defined on the independent sets of an undirected graph. Given two independent sets $I$ and $J$, each of size $k$, these problems ask whether there exists a sequence of elementary operations transforming $I$ into $J$ such that every intermediate configuration is also an independent set of size $k$. In Sliding Token, an operation moves a token from a vertex $u \in I$ to an adjacent vertex $v \notin I$; in Token Jumping, the token may instead move to any vertex $v \notin I$. While both problems are PSPACE-complete on general graphs, polynomial-time algorithms have been developed for several graph classes, including trees, block graphs, cacti, bipartite permutation graphs, cographs, $P_4$-tidy graphs, and interval graphs.
In this paper, we prove that both problems are solvable in polynomial time on threshold signed graphs, also known as Dilworth-2 graphs. A graph $G=(V,E)$ is a threshold signed graph if there exist a mapping $a:V\to\mathbb{R}$ and positive real constants $S$ and $T$ such that, for any distinct vertices $u,v\in V$, $\{u,v\}\in E$ if and only if $|a(u)+a(v)|\ge S$ or $|a(u)-a(v)|\ge T$. This graph class is a subclass of permutation graphs, for which the complexity of these problems remains open, and is incomparable with the class of bipartite permutation graphs studied by Fox-Epstein et al. (ISAAC, 2015). The algorithm is based on the inclusion-chain structure that characterises threshold signed graphs, a structural property that may be of independent interest.
arXiv:2607.10630v1 Announce Type: new
Abstract: Robust motion planning in dense traffic requires autonomous vehicles to interact in rare and safety-critical scenarios that are underrepresented in naturalistic driving data. Although adversarial training offers a feasible solution, existing methods often rely on external scenario generators, heuristic perturbations, or simulator-heavy rollouts, which makes them difficult to integrate with modern autoregressive planners. Here, we cast adversarially robust planner learning as a constrained min-max game and propose Adversarial World Modeling (AWM), a theoretically grounded multi-agent self-play fine-tuning framework. Since solving the exact game is intractable, AWM introduces a principled decoupled solver. In the inner minimization, the planner's predictive world model is converted into a role-conditioned adversary that learns sparse, scene-adaptive attack coalitions via counterfactual credit assignment. In the outer maximization, the ego planner optimizes a regret-aware robust best response against the frozen AWM, utilizing tail-risk weighting and reference-anchored trust regions to improve hard-case recovery while preserving nominal driving behavior. Experiments on the nuPlan and InterPlan benchmarks demonstrate that our method generates transferable adversarial interactions and yields a robust planner that achieves competitive closed-loop performance in both nominal and highly interactive long-tail scenarios. Theoretical analysis justifies the decoupled solver and the main optimization components.
arXiv:2607.10803v1 Announce Type: new
Abstract: Understanding which parameters are influential in Large Language Models (LLMs) is central to improving their efficiency, reliability, and interpretability. We introduce Weight-Adjusted Gradients (WAG), a simple yet effective approach for estimating parameter importance that explicitly captures the interaction between model weights and first-order gradient information and identifies parameters that disproportionately influence model behavior, such as those responsible for collapse phenomena in LLMs. Across a range of models and settings, we show that WAG surfaces a tiny but critical subset of parameters whose modification leads to dramatic degradation in performance, a failure mode that existing importance metrics overlook. These findings reveal a previously underexplored interplay between weights and gradients, suggesting that parameter importance cannot be fully understood through either signal alone. The surprising effectiveness of WAG points to fundamental structural properties of trained networks and motivates new open questions about the role of zeroth-order and first-order information in deep learning. We demonstrate the practical utility of WAG across multiple applications, including expert allocation in mixture-of-expert architectures, parameter-specific unlearning, mixed-precision quantization, and layer selection for knowledge editing. Our results position WAG as a unified approach for analyzing, debugging, and controlling LLMs, and opens new directions for principled model-level interpretation.