arXiv:2602.23024v5 Announce Type: replace
Abstract: Mobile manipulation is a fundamental capability for general-purpose robotic agents, requiring both coordinated control of the mobile base and manipulator and robust perception under dynamically changing viewpoints. However, existing approaches face two key challenges: strong coupling between base and arm actions complicates control optimization, and perceptual attention is often poorly allocated as viewpoints shift during mobile manipulation. We propose InCoM, an intent-driven perception and structured coordination framework for mobile manipulation. InCoM infers latent motion intent to dynamically reweight multi-scale perceptual features, enabling stage-adaptive allocation of perceptual attention. To support robust cross-modal perception, InCoM further incorporates a geometric-semantic structured alignment mechanism that enhances multimodal correspondence. On the control side, we design a decoupled coordinated flow matching action decoder that explicitly models coordinated base-arm action generation, alleviating optimization difficulties caused by control coupling. Experimental results demonstrate that InCoM significantly outperforms state-of-the-art methods, achieving success rate gains of 28.2%, 26.1%, and 23.6% across three ManiSkill-HAB scenarios without privileged information. Furthermore, its effectiveness is consistently validated in real-world mobile manipulation tasks, where InCoM maintains a superior success rate over existing baselines.
Science Journals
arXiv:2603.27250v2 Announce Type: replace
Abstract: Prompt-conditioned foundation segmenters have emerged as a dominant paradigm for image segmentation, where explicit spatial prompts(e.g., points, boxes, masks) guide mask decoding. However, many real-world deployments require fully automatic segmentation, creating a structural mismatch: the decoder expects prompts that are unavailable at inference. Existing adaptations typically modify intermediate features, inadvertently bypassing the model's native prompt interface and weakening prompt-conditioned decoding. We propose IP-SAM, which revisits adaptation from a prompt-space perspective through prompt-space conditioning. Specifically, a Self-Prompt Generator (SPG) distills image context into complementary intrinsic prompts that serve as coarse regional anchors. These cues are projected through SAM2's frozen prompt encoder, restoring prompt-guided decoding without external intervention. To suppress background-induced false positives, Prompt-Space Gating (PSG) leverages the intrinsic background prompt as an asymmetric suppressive constraint prior to decoding. Under a deterministic no-external-prompt protocol, IP-SAM achieves state-of-the-art performance across four camouflaged object detection benchmarks with only 21.26M trainable parameters. Furthermore, the proposed conditioning strategy generalizes beyond COD to medical polyp segmentation.
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning
arXiv:2604.02721v2 Announce Type: replace
Abstract: Competitive programming remains one of the last few human strongholds in coding against AI. The best AI system to date still underperforms the best humans competitive programming: the most recent best result, Google's Gemini~3 Deep Think, attained 8th place even not being evaluated under live competition conditions. In this work, we introduce GrandCode, a multi-agent RL system designed for competitive programming. The capability of GrandCode is attributed to two key factors: (1) It orchestrates a variety of agentic modules (hypothesis proposal, solver, test generator, summarization, etc) and jointly improves them through post-training and online test-time RL; (2) We introduce Agentic GRPO specifically designed for multi-stage agent rollouts with delayed rewards and the severe off-policy drift that is prevalent in agentic RL. GrandCode is the first AI system that consistently beats all human participants in live contests of competitive programming: in the most recent three Codeforces live competitions, i.e., Round~1087 (Mar 21, 2026), Round~1088 (Mar 28, 2026), and Round~1089 (Mar 29, 2026), GrandCode placed first in all of them, beating all human participants, including legendary grandmasters. GrandCode shows that AI systems have reached a point where they surpass the strongest human programmers on the most competitive coding tasks.
arXiv:2604.03922v2 Announce Type: replace
Abstract: Selecting LLM-generated code candidates using LLM-generated tests is challenging because the tests themselves may be incorrect. Existing methods either treat all tests equally or rely on ad-hoc heuristics to filter unreliable tests. Yet determining test correctness requires knowing which codes are correct, creating a \emph{circular dependency}. Our key insight is that we need not determine test correctness at all: \emph{test votes should rank, not merely count}. What matters is not how many codes pass a test, but whether the test can \emph{distinguish} correct from incorrect code. We break the circular dependency via leave-one-out evaluation: hold out one test, rank codes by their aggregate scores on all remaining tests, and measure whether the held-out test's pass/fail pattern agrees with this ranking. We formalize this agreement as the leave-one-out AUC~(LOO-AUC) and prove that the expected LOO-AUC is proportional to each test's ability to separate correct code from incorrect code. Building on this, we propose \textbf{ACES}~(\textbf{A}UC \textbf{C}onsist\textbf{E}ncy \textbf{S}coring) with two complementary variants: ACES-C provides closed-form weights that provably approximate the oracle in expectation under a mild assumption on average test quality; ACES-O drops this assumption and iteratively optimizes a differentiable LOO-AUC objective. Both operate solely on the binary pass matrix with negligible overhead, and achieve state-of-the-art Pass@$k$ on multiple code generation benchmarks.
arXiv:2607.11310v1 Announce Type: new
Abstract: Physics-Informed Neural Networks (PINNs) provide a meshless approach for solving partial differential equations (PDEs), but suffer severe degradation in stiff and shock-dominated problems, where small PDE residuals can correspond to globally inaccurate solutions. We show these failures are multi-causal, arising from the concurrent interplay of (i) spectral bias against sharp features, (ii) imbalanced multi-term optimization and loss-weight collapse, (iii) violation of temporal causality, and (iv) under-resolved collocation. We present SPARC-Net, a unified architecture and training framework that jointly addresses all four pathologies. SPARC-Net leverages an adaptive multi-scale spectral encoder with a learnable spectral gate, a gated residual backbone, adaptive activations, and a hard-constraint output ansatz that exactly enforces initial and boundary conditions, structurally eliminating loss-weight collapse. Training employs stabilized gradient-norm loss balancing, floored causality-respecting residual weighting, and residual-based adaptive collocation (RAD). Validated against exact analytic and high-order spectral reference solutions across four canonical benchmarks -- viscous Burgers', Allen-Cahn, convection (beta=30), and reaction -- SPARC-Net yields substantial improvements over vanilla PINNs: relative L2 error drops from 1.47e-1 to 1.14e-1 on Burgers' (22% reduction), 9.93e-1 to 5.78e-2 on Allen-Cahn (94% reduction), and 9.82e-1 to 3.54e-3 on reaction (100% reduction). A characteristic-coordinate encoder for hyperbolic transport further reduces convection error from 5.14e-1 to 9.88e-5 (100% reduction). We report five-seed mean +/- standard deviation errors, Wilcoxon significance tests, full ablation studies, hyperparameter sensitivities, an extension to the 2D heat equation, and comparisons against parameter-matched baselines.
arXiv:2607.11267v1 Announce Type: new
Abstract: In the rapidly evolving landscape of information retrieval systems, the ability to adapt and improve through user feedback is paramount. This study introduces a novel methodology for refining the performance of a primary Retrieval Augmented Generation (RAG) system by strategically integrating an auxiliary feedback RAG system. By systematically harnessing human-generated feedback, the approach aims to enhance the accuracy, relevance, and overall quality of responses, driving the system towards self-improvement. Central to this methodology is a human-in-the-loop implementation, where user feedback is continuously collected, classified, and integrated into the inference workflow, enabling the system to learn and evolve iteratively. To validate the effectiveness of this approach, the study employs rigorous testing against three diverse benchmark datasets focused on general and custom domain knowledge, utilizing a LLM-as-a-Judge evaluation strategy. This comprehensive framework not only underscores the transformative potential of feedback-driven enhancements in RAG systems but also sets a precedent for future research in adaptive information retrieval technologies, marking a significant step in the journey towards autonomous refinement and optimization through user engagement.
arXiv:2607.11364v1 Announce Type: new
Abstract: Generating immersive, synchronized and cinematic audio for long-form textual narratives remains a significant challenge in multi-modal AI. While current Text-to-Audio (TTA) frameworks successfully synthesize isolated sound effects, they struggle with narrative cohesion, temporal alignment, and cinematic emotional depth. We present BackgroundMellow, a framework that treats story-to-audio generation as a precise orchestration and signal processing problem. This framework is enabled without ground-truth through a master-specialist agent architecture that decomposes text into precise and multi-layered audio cues, generates each category of sounds with suitable specialist model, and superimposes the soundscapes to create a unified and aligned audio segment. Our pipeline is built over Tango2 latent diffusion model for environmental synthesis alongside a novel Cinematic BGM Retriever mined from professional soundtracks. To automate the sound mixing process, we use an NLP based module that predicts precise audio parameters, like start time, duration, and relative loudness, based on the narrative timeline. We further empirically evaluate and show the efficacy of the proposed framework leveraging nearest-neighbor retrieval against a curated dataset of YouTube cinematic trailers to measure temporal synchronization, coverage, and spectral richness.
arXiv:2607.09732v1 Announce Type: new
Abstract: We constrain three holographic-inspired dark energy models, namely holographic dark energy (HDE), agegraphic dark energy (ADE), and Ricci dark energy (RDE), using late-time observations from cosmic chronometers, Type Ia supernovae (SNe Ia), DESI DR2 baryon acoustic oscillations (BAO), and {redshift-space distortion (RSD) growth measurements}. Five data combinations are considered: $H(z)+$Pantheon+, $H(z)+$DESI DR2+Pantheon+, $H(z)+$DESI DR2+DES-Dovekie, $H(z)+$DESI DR2+DESY5, and {$H(z)+$DESI DR2+DES-Dovekie+RSD}. We perform Bayesian Markov chain Monte Carlo parameter estimation and compare the models with AIC and BIC. In the BAO-included combinations, HDE gives $H_0\simeq67.3$--$68.0~\mathrm{~km~s^{-1}~Mpc^{-1}}$, $\Omega_{m0}\simeq0.270$--$0.272$, and $c\simeq1$, indicating an expansion history close to the de Sitter boundary rather than a robust phantom regime. ADE yields a stable agegraphic parameter $n\simeq2.78$--$2.81$, while RDE gives $\gamma\simeq0.53$--$0.55$ and persistently favors a low matter density, $\Omega_{m0}\simeq0.215$--$0.219$. {Treating $r_d$ as a free parameter reveals a strong negative correlation between $H_0$ and $r_d$, and the RSD-included combination provides a growth-level consistency check through $f\sigma_8(z)$ without constituting a full perturbative stability analysis.} None of the three models significantly alleviates the Hubble tension. Overall, HDE shows the most balanced phenomenological behavior among the three models, although current late-time data do not decisively prefer it over $\Lambda\text{CDM}$.
arXiv:2607.10197v1 Announce Type: new
Abstract: Knowledge graph foundation models such as Ultra and Trix achieve strong inductive transfer by learning relation-graph representations that generalise to unseen entities and relations. Extending this transferability to temporal knowledge graphs (TKGs) remains challenging: existing temporal models tie their parameters to dataset-specific entities, relations, or timestamps and are not designed to transfer to TKGs with disjoint vocabularies. We propose GRATE (Gated Rotary Attention for Temporal Encoding), an entity-side message function that adds no learnable parameters and encodes time through relative time differences by rotating each edge message according to its time gap to the query and applying a query-conditioned gate to select temporally relevant signals. GRATE integrates into NBFNet-style KG foundation models while preserving structural transferability. Existing TKG benchmarks evaluate within shared train/test vocabularies and cannot directly test cross-dataset temporal transfer; we therefore construct GDELTIndT and WIKIIndT, inductive transfer benchmark suites with disjoint entities, relations, and timestamps spanning both interpolation and extrapolation. Across these benchmarks and held-out forecasting datasets, a single jointly pretrained GRATE checkpoint improves over the static base model in most settings.
arXiv:2607.11287v1 Announce Type: new
Abstract: Comprehensive quantification of cardiac structures from computed tomography (CT) remains limited not by data availability but by the scalability of measurements, which makes routine use impractical. Here we present a unified framework for comprehensive cardiac CT segmentation and phenotyping that combines a human-in-the-loop annotation pipeline, a cardiac CT augmentation technique, and a self-supervised foundation model pre-trained on 60,000 unlabeled cardiac CT scans. Using this approach, we assembled the largest and most comprehensive expert-annotated cardiac CT segmentation dataset to date, comprising 1598 cases and 14 distinct cardiac structures (1000 for training, 598 for the external test set). Across five external datasets, the framework segmented all structures more accurately and comprehensively than existing open-source tools. Self-supervised pre-training improved labeling efficiency, with the most significant gains observed during external evaluation in the low-data regime. Benchmarking across convolutional, transformer, and state-space architectures showed comparable performance, indicating that data quality and pre-training, rather than architecture, drove accuracy. The framework was scaled to population-level phenotyping, with segmented anatomy that carries functionally relevant information about ventricular function and disease severity beyond demographic variables. By openly releasing the largest dataset with human labels, code, model weights, a CT augmentation library, and software, this work provides a reproducible foundation for opportunistic cardiac phenotyping from routinely acquired CT scans.
arXiv:2607.11288v1 Announce Type: new
Abstract: We introduce the Self-Evolving Agentic Operating System (SE-AOS): a new class of AI agent that treats exploit capability as a mutable, versioned kernel it extends at runtime, observing its own failures, synthesising new capabilities, proving them against a live target, and hot-loading them back into itself. Mako is the first SE-AOS instance for security research and the autonomous web exploitation engine developed within LaunchSafe. LaunchSafe builds autonomous security agents for continuous offensive testing and agent-driven security research; Mako is the core engine behind that platform. On the public XBOW validation-benchmarks, 104 containerised, CTF-style web applications spanning 26 vulnerability classes across three difficulty tiers, Mako achieves full-suite coverage: it drives every one of the 104 targets to emit a cryptographically fresh, per-build flag, under a verification regime that makes fabricated or memorised results impossible. Our central result is a law of autonomous exploitation: once a capability exists and is discoverable, difficulty collapses; capability, not reasoning, is what is scarce, together with an architecture and formalism that turn that law into a self-improving system. Mako further runs a gated self-evolution loop that proposes, sandboxes, and commits improvements to its own agents and rules when fitness does not regress. We deliberately withhold the operational results, payloads, exploit chains, and tool source, because a system that reduces full-spectrum web exploitation to a repeatable, machine-speed pipeline is dual-use research of concern. We publish the science; we withhold the weapon.
arXiv:2607.10703v1 Announce Type: new
Abstract: Rectilinear matching to the integer grid asks to assign each of $n$ points in $\mathbb R^2$ to a distinct point of $\mathbb Z^2$, minimizing total $\ell_1$ movement. The main difficulty is that the target set is infinite: one must first identify a finite set of relevant grid points without losing optimality.
We prove a geometric compression theorem for this infinite-target problem. In $O(n\log^2 n)$ time, we construct a set $\mathcal{C}$ of asymptotically optimal size $O(n)$ such that, simultaneously for every $p\in[1,\infty]$, some optimal $\ell_p$ assignment uses only points of $\mathcal{C}$. The construction is independent of the subsequent optimization algorithm and of the coordinate spread.
For the rectilinear case, we combine this candidate set with a linear-size sparse network representation of $\ell_1$ distances. In the word-RAM model with $O(1)$-word dyadic coordinates and $O(\log n)$ fractional bits, a nearly-linear time minimum-cost flow algorithm then gives a randomized exact algorithm with expected running time $\widetilde O(n)$. This improves the standard $\widetilde O(n^2)$ approach. Combined with existing finite geometric matching algorithms, the same candidate set also gives an $\widetilde O(n\sqrt n\log(1/\varepsilon))$-time $(1+\varepsilon)$ approximation for every fixed integer $p\ge1$.
arXiv:2607.10706v1 Announce Type: new
Abstract: The action space poses a major challenge in robot learning, since it is often high-dimensional, can span long time horizons, and frequently admits multi-modal optimal solutions. A good choice of action representation and loss function can help to address these concerns, but there are often trade offs. We propose Action Map Policy (AMP), which casts 3D closed-loop manipulation policy learning as a classification problem in image space. While classification has been an effective formulation in generative language models, applying it to robot action learning is difficult because naively discretizing high-dimensional continuous actions explodes the token vocabulary. Our key idea is to project 3D actions onto the camera image planes and treat each pixel location as a discrete class, thus controlling dimensionality while retaining multi-modality. This method supports millimeter-level precision for high-dimensional actions without requiring a prohibitively large vocabulary, while preserving fine-grained pixel-wise visual signals. Furthermore, it can predict the entire action chunk in a single forward pass, avoiding complex noise scheduling and iterative denoising while achieving substantially faster inference than diffusion policies. Experiments on various manipulation tasks show that AMP outperforms strong baselines, achieving higher success rates, faster inference, and enhanced spatial reasoning.
arXiv:2601.07372v2 Announce Type: replace
Abstract: While Mixture-of-Experts (MoE) scales capacity via conditional computation, Transformers lack a native primitive for knowledge lookup, forcing them to inefficiently simulate retrieval through computation. To address this, we introduce conditional memory as a complementary sparsity axis, instantiated via Engram, a module that modernizes classic $N$-gram embedding for O(1) lookup. By formulating the Sparsity Allocation problem, we uncover a U-shaped scaling law that optimizes the trade-off between neural computation (MoE) and static memory (Engram). Guided by this law, we scale Engram to 27B parameters, achieving superior performance over a strictly iso-parameter and iso-FLOPs MoE baseline. Most notably, while the memory module is expected to aid knowledge retrieval (e.g., MMLU +3.4; CMMLU +4.0), we observe even larger gains in general reasoning (e.g., BBH +5.0; ARC-Challenge +3.7) and code/math domains~(HumanEval +3.0; MATH +2.4). Mechanistic analyses reveal that Engram relieves the backbone's early layers from static reconstruction, effectively deepening the network for complex reasoning. Furthermore, by delegating local dependencies to lookups, it frees up attention capacity for global context, substantially boosting long-context retrieval (e.g., Multi-Query NIAH: 84.2 to 97.0). Finally, Engram establishes infrastructure-aware efficiency: its deterministic addressing enables runtime prefetching from host memory, incurring negligible overhead. We envision conditional memory as an indispensable modeling primitive for next-generation sparse models.
arXiv:2603.05283v3 Announce Type: replace
Abstract: We reformulate the neutral wealth tax framework of Froeseth (2026; arXiv:2603.05264) in the language of stochastic dynamics and statistical physics. Individual wealth under geometric Brownian motion satisfies a Langevin equation with multiplicative noise; the probability density of wealth across a population then evolves according to a Fokker-Planck equation. A proportional wealth tax at market value enters as a uniform reduction of the drift coefficient, preserving the diffusion structure and all relative probability currents. This drift-shift symmetry is the physical content of tax neutrality. Each channel through which neutrality breaks down in practice - book-value assessment, liquidity frictions, forced dividend extraction, migration, and market impact - corresponds to a specific violation of this symmetry: a state-dependent, asset-dependent, or flow-dependent modification of the Fokker-Planck equation. The framework clarifies when wealth taxation is a benign rescaling of the dynamics and when it introduces genuinely new physics.
arXiv:2604.01087v2 Announce Type: replace
Abstract: Dynamic Spectrum Sharing (DSS) enables flexible activation of additional spectrum resources but leaves open a key runtime question: once new spectrum becomes available, which steering mechanism should migrate connected devices toward it with minimum service disruption? We present the first PHY-aware characterization of 3GPP-compliant UE steering mechanisms, including Bandwidth Part (BWP) reconfiguration, Carrier Aggregation (CA), E-UTRA-NR Dual Connectivity (EN-DC), Connected-Mode Handover (HO), and Release and Redirection (R&R), using modem-level traces from devices connected to operational networks, collected across 1,600 executions over four months in 12 urban areas. By mapping each mechanism to observable PHY-layer milestones, we decompose steering latency into intrinsic PHY-centric execution and RRC-to-PHY completion components, revealing substantial heterogeneity: NR BWP achieves 6.25 ms mean latency with zero tail exceedance above 50 ms, while CA exceeds 1225 ms; mobility procedures remain largely modem-bound, whereas discovery-driven mechanisms experience significant RRC-to-PHY completion amplification. Guided by these measurements, we design POLARIS, an O-RAN-based system that selects the least disruptive steering mechanism via a two-parameter disruption score. POLARIS reduces mean latency by up to 85.1% and T95 by 89.7% over static or non-adaptive baselines, eliminates tail exceedance above 50 ms, and avoids high-disruption mechanisms, demonstrating that PHY-layer execution profiling enables reliable and context-aware spectrum steering in DSS-enabled networks.
arXiv:2607.11347v1 Announce Type: new
Abstract: Neural networks increasingly guide decisions in high-stakes domains such as medical diagnosis, credit approval, and energy bidding. Audit in these settings requires case-level evidence: which training cases support an action and what outcomes they carried. Case-based decision theory (CBDT) formalizes this reasoning by aggregating outcome support from remembered cases. We show that an OLS action readout fitted on a fixed neural representation admits an exact case-based decomposition. Each action score is a weighted sum of training-case returns, with coefficients determined by empirical Gram geometry. We identify a sufficient regime for CBDT similarity semantics; outside it, the coefficients should generally be treated as signed Gram-geometric influence. The decomposition yields audit signals that trace scores to training cases, measure action coherence, and identify weak support. Across synthetic CBDT, PJM, Adult Income, and Default Credit tasks, the method recovers case-level preference structure and achieves the highest mean Top-30 consistency among compared attribution baselines, while remaining competitive on support reconstruction. The audit requires only fitting an OLS top-layer probe, without retraining the representation or accessing the original optimization trajectory; probe fidelity is measured by score reconstruction.
arXiv:2607.11400v1 Announce Type: new
Abstract: Legal information processing spans retrieval, entailment and judgment prediction problems, requiring text matching, reasoning and robust generalisation with limited supervision. We report Team DU's participation in all five tasks of COLIEE 2026, using open-weight systems for legal case retrieval, case entailment, statute retrieval and entailment, and legal judgment prediction. For Tasks 3 and 4, all models predate the 15 July 2025 cutoff required by the rules. For Task 4 (statute entailment), a cross-architecture ensemble of nine models from three families achieves 96.3% accuracy, placing first among 33 submissions from 11 teams. For the Pilot Task (tort prediction and rationale extraction), a multi-view system combining five claim-level models and refining the verdict using features derived from the claim predictions achieves 73.1% TP accuracy and 68.2% RE F1 as an unofficial submission, scoring above all official entries on TP and matching the highest on RE. For Task 2 (legal case entailment), changing only the prompt from single- to multi-selection raises F1 from 0.343 to 0.555 in post-competition evaluation on released gold labels, exceeding the best official submission (F1 = 0.490). For Task 3 (statute retrieval and entailment), replacing the entailment model with Qwen3-235B and a structured legal reasoning prompt raises accuracy from 79.3% to 91.5% in post-competition analysis. For Task 1 (legal case retrieval), a learning-to-rank system combining lexical and semantic retrieval with structural, citation authority, and temporal features (34 in total) achieves F1 = 0.314 (rank 11 of 54 submissions from 22 teams). Overall, legal information processing benefits from different inductive biases across tasks, with cross-architecture ensembling, feature-based reranking and retrieval-augmented prompting each proving most effective in different settings.
arXiv:2607.09923v1 Announce Type: new
Abstract: This research presents a novel hybrid image encryption system that combines quantum cryptography, chaos theory and reservoir computing to address the limitations of conventional encryption methods. With the rapid advancements in quantum computing, traditional systems like RSA, DHKE (related to prime number factorization) are vulnerable to quantum attacks i.e. Shor's algorithm, Grover's algorithm. In response, this study proposes a hybrid solution that uses quantum cryptographic protocols, particularly the E91 protocol, to generate secure, eavesdrop-proof keys through quantum entanglement. The integration of chaos theory, specifically the Lorenz hyper-chaotic system, enhances the encryption system by adding unpredictability and sensitivity to initial conditions, making it more resistant to both classical and quantum-based attacks. Reservoir computing is used to improve computational efficiency, enabling faster and more effective encryption and decryption processes. The system achieved encryption times as low as 0.0296s and decryption times as low as 0.0164s for 128x128 images, with MAE reduced for 300-600 node networks, and NPCR and UACI above 99.6% and 0.49, respectively, across various image sizes and configurations. By combining quantum cryptography, chaos theory and reservoir computing, this approach offers both enhanced security and practical feasibility for image encryption in the age of quantum computing.
arXiv:2607.09727v1 Announce Type: cross
Abstract: WiFi sensing based on Channel State Information (CSI) promises ubiquitous, device-free perception, yet current research remains trapped in a Tower of Babel - fragmented into isolated silos where models are tailored to specific hardware dialects, fixed environments, and narrow tasks. The primary bottleneck is the Heterogeneity Gap: the disparity in signal dimensions, sampling rates, and semantic labels that prevents cross-system understanding. To bridge this gap, we propose a foundation-model framework that treats CSI not merely as raw signals but as a structured language with a learnable universal grammar. We first curate and standardize a large collection of heterogeneous real-world CSI datasets, establishing a unified infrastructure that allows incompatible signal formats to be treated as a single corpus. Second, we introduce a modular architecture that acts as a universal translator where lightweight dataset-specific adapters tokenize diverse signal inputs into a shared latent vocabulary, while a shared self-supervised Transformer backbone learns the temporal syntax of human motion and environmental dynamics. This design decouples sensing semantics from hardware syntax. Extensive evaluations show that by mastering this universal language, our approach consistently outperforms task-specific baselines and exhibits strong generalization capability in new environments, achieving superior efficiency in few-shot scenarios. By effectively absorbing heterogeneity, the framework offers a path toward robust, general-purpose wireless sensing, mirroring the linguistic generalization observed in Large Language Models. The code implementation is available at: https://github.com/cjychenjiayi/WiLLM.
arXiv:2607.11348v1 Announce Type: new
Abstract: AI code assistants are transforming software development, but their implications for software security remain a major concern, particularly in the context of security APIs. These APIs are critical for safeguarding software systems, yet their complexity often leads to incorrect use and serious vulnerabilities. Developing an evidence-based understanding of how AI assistants influence developers' use of these APIs is therefore essential for informing effective mitigation strategies. While a few user studies have examined the broader impact of AI assistants on software vulnerabilities, the use of security APIs remains unexplored from a developer-centered perspective. This study addresses this gap by presenting the first empirical investigation into how AI code assistants affect professional developers' use of security APIs. We conducted a study with 44 developers who completed security API programming tasks with and without GitHub Copilot assistance. Our findings show that, while Copilot improves functional correctness and marginally reduces certain insecure patterns, it does not significantly improve secure API usage. We also found that developers rarely raised security concerns when engaging with Copilot, and many did not recognize that their final implementations remained insecure. Finally, we offer recommendations for enhancing security awareness among developers and propose future research directions to support safer AI-assisted software development.
arXiv:2607.11352v1 Announce Type: new
Abstract: Intuitionistic modal logic (IML) has inspired several developments in programming languages including modal type systems for staging, computational effects and language-based security. IMLs are typically studied using Kripke-style relational semantics, which simplifies proofs of meta-theoretic properties, such as completeness and consistency, by making it easy to construct models. Kripke-style relational semantics, however, relies upon classical reasoning principles, which makes it unappealing from a computational perspective and unsuitable for formalization in a constructive type theory. Goldblatt provides an alternative semantics for IMLs by extending Beth-Kripke-Joyal-style "cover" semantics for intuitionistic propositional logic with relations to support modalities. Goldblatt's "relational cover" semantics overcomes classical reasoning but introduces a new limitation: it relies upon a "modal localization" condition that restricts the class of models and complicates model construction. Goldblatt bypasses this restriction by using intricate order-theoretic completion arguments to prove completeness. In this article, we present a conservative extension of relational cover semantics that alleviates this restriction and is amenable to simpler and standard model construction techniques. We formalize our semantics in Agda and prove completeness constructively in the style of Normalization by Evaluation for a variety of IMLs featuring independent box and diamond modalities.
arXiv:2607.10991v1 Announce Type: new
Abstract: As mobile robots become more integrated into everyday human environments, social robot navigation is becoming essential for ensuring human comfort, safety, and trust. While reinforcement learning (RL) navigation policies provide the fast inference and reactive behavior necessary for real-time deployment, they still lack flexible semantic reasoning capabilities and often fail to generalize to complex social scenarios. Recent approaches have increasingly turned to vision-language models (VLMs) in place of RL policies to improve semantic and social reasoning in robot navigation. Nevertheless, their high computational cost and slow inference remain major barriers to real-time deployment. To overcome these limitations, we introduce HUMA (Hybrid Understanding for Multi-modal social Navigation), a hybrid architecture that dynamically balances the computational efficiency of RL policies with the deep semantic understanding of VLMs. Our approach uses a reactive RL policy to handle low-density, routine navigation tasks, while conditioning it on a post-trained high-level VLM when a human enters sensitive situations, such as the robot's proximity zone. We evaluate HUMA on the Social-MP3D and Social-HM3D benchmarks, where it achieves task success improvements of 20% and 3%, respectively, while significantly reducing personal space violations and human collisions against state-of-the-art baselines. Extensive ablation studies validate each architectural component, and real-world deployment on the Miroka\"i mobile robot further demonstrates the practical viability of our approach.
arXiv:2607.11358v1 Announce Type: new
Abstract: Automatic Heuristic Design (AHD) has emerged as a transformative approach for solving combinatorial optimization problems. While recent Large Language Model (LLM)-based methods have shown promise, they predominantly rely on fixed evolutionary operators and struggle to effectively accumulate and reuse historical search experience. This paper proposes RefineEvo, a novel evolutionary framework that transforms AHD from a static trial-and-error process into a planning-guided, experience-driven system. RefineEvo introduces a Planner to dynamically schedule evolutionary operators and trigger refinement based on the current search state, and a Reflector to distill valuable lessons into a Bidirectional Experience Pool containing both positive insights and negative pitfalls. This synergistic framework enables the system to adapt its search tools to the evolving complexity of the problem and leverage trajectory-aware, situation-conditioned insights to guide generation. Experiments on several classic combinatorial optimization benchmarks demonstrate that RefineEvo consistently outperforms strong baselines. In particular, RefineEvo delivers superior solution quality while improving token efficiency, enabling more efficient and autonomous heuristic design.
arXiv:2607.09876v1 Announce Type: new
Abstract: Automatically retrieving videos from large camera-trap datasets remains challenging. Text-to-Video retrieval (TVR) methods based on large video-language models (VLMs) have potential to retrieve events of interest by describing them with simple text queries. However, current methods often lack spatiotemporal understanding and do not generalize well to ecological data. In this work, we introduce Prompting-MammAlps, the first camera-trap TVR benchmark, and propose a fine-grained and interpretable TVR method. Specifically, we trained a vision transformer to perform spatiotemporal action localization, and convert its output to structured text, describing each video. Independently, ethology-inspired queries are processed by a Large-Language Model (LLM) based coding agent to parse the structured text per video and retrieve videos accordingly. We harnessed the LLM to use functions from a custom parsing library to minimize the risk of LLM hallucinations and to improve method interpretability. This retrieval approach applied on the Prompting-MammAlps benchmark achieved a set-based F1-score of 34\% on a test set of 135 ecologically-relevant queries and 775 candidate videos. In comparison the best zero-shot VLM achieved a F1-score of 18\%, while also lacking interpretability. Project page: https://cnai.epfl.ch/prompting-mammalps