arXiv:2607.14643v1 Announce Type: new
Abstract: End-to-end diffusion-based policies have demonstrated strong performance in mapless visual navigation, but their iterative denoising process introduces substantial inference latency, while behavior cloning limits performance to the quality of expert demonstrations. We present NavCMPO, a two-stage adaptive navigation framework that combines few-step MeanFlow trajectory generation, critic-guided refinement, and reinforcement learning fine-tuning. During pre-training, an obstacle proximity prediction task encourages the visual representation to capture obstacle-aware spatial information. To compensate for the degradation in obstacle avoidance caused by few-step generation, Critic-Guided Trajectory Refinement (CGTR) uses gradients from a critic trained with obstacle-point-cloud supervision to refine intermediate trajectories. During adaptation, the MeanFlow policy is fine-tuned using Proximal Policy Optimization with behavior-cloning regularization, while the critic is updated to accommodate embodiment-specific observation changes. Under a matched training budget on the InternVLA-N1 benchmark, NavCMPO achieves an average success rate of 74.7\%, exceeding the retrained NavDP baseline by 6.4 percentage points, while reducing inference latency from 85\,ms to 60\,ms. Experiments on a Unitree Go2 further demonstrate effective sim-to-real transfer.
Science Journals
arXiv:2607.14644v1 Announce Type: new
Abstract: In the semi-streaming model, we have an $n$-vertex graph $G=(V,E)$ whose edges arrive in an arbitrary order in a stream. The goal is to make one or a few passes over the stream, use a limited memory of $\tilde O(n)$ bits, and output a solution to the problem at hand at the end. A central open question in this area is to determine the best approximation ratio possible for the maximum matching problem via single-pass semi-streaming algorithms.
This problem admits a simple $0.5$-approximation algorithm, by maintaining a maximal matching greedily, which, despite extensive efforts, has remained the state of the art. Lower bounds for this problem have also been few and far between with best known bounds ruling out better than $1/(1+\ln{(2)}) \sim 0.590$ approximation, using a highly complicated construction motivated by the literature on RS graphs from extremal graph theory.
We develop a new framework for proving lower bounds for the semi-streaming matching problem. Our framework abstracts out the extremal graph theory and information theoretic arguments in the lower bounds, and reduces the problem to constructing certain constant-size graphs, which we call blueprints. Not only existing lower bounds can be captured by these blueprints, leading to far simpler and more concise arguments, but also we can design new blueprints that can be used to rule out $(8-2\sqrt{10})/3 \sim 0.558$-approximation for the semi-streaming matching problem. We believe this approach can be of its own independent interest and lead to further improvements on this tantalizing open question.
arXiv:2607.14645v1 Announce Type: new
Abstract: This work introduces FilmGPT, an autoregressive transformer designed to address the challenge of video montage--turning a collection of raw, "unwatchable" footage into coherent cinematic sequences. Inspired by language learning in modern LLMs, we train a long-context autoregressive transformer on a large corpus of movies. The aim is to implicitly capture the "grammar" of film directly from data rather than from hand-coded rules. Unlike other generative models, FilmGPT does not generate any new video frames. Instead, at inference time, we introduce a footage-constrained decoding algorithm to select the best next shot from the input raw footage according to the statistical patterns learned from films. We first evaluate these learned statistics directly by using the FilmGPT autoregressive model for next shot prediction on a standard benchmark of shot sequence ordering, outperforming the previous state of the art. We then evaluate our footage-constrained decoding algorithm on the full film editing task via a user study, and find that our FilmGPT-based editing significantly outperforms previous approaches. Finally, we demonstrate the applicability of FilmGPT to a wide range of applications in video montage, from automatic video segment trimming to human-in-the-loop film editing.
arXiv:2607.14647v1 Announce Type: new
Abstract: Speculative decoding accelerates large language model (LLM) inference without compromising output quality. Recent parallel drafting methods further improve single-request performance by decoupling draft length from drafting latency, enabling longer drafts and higher mean accepted tokens (MAT). However, under high request concurrency, long drafts waste substantial computation on rejected tokens, increasing verification cost and potentially making speculative decoding slower than autoregressive decoding. We present D-Cut, an adaptive pruning method that selects draft tokens jointly across the batch and concentrates the verification budget on tokens most likely to be accepted. D-Cut is motivated by two observations. First, acceptance lengths vary considerably across concurrent requests; D-Cut therefore performs cross-request pruning, allocating the verification budget adaptively according to draft confidence. Second, verification cost depends strongly on the deployment environment, including GPU architecture and parallelism strategy; D-Cut incorporates a runtime cost model to adapt its pruning depth to the target environment. Experiments on dense and mixture-of-experts (MoE) models show that, under high concurrency, D-Cut improves the average speedup from \(1.26\times\) to \(1.65\times\), restores acceleration in dense-model configurations where long-draft baselines are slower than autoregressive decoding, and achieves up to \(3.0\times\) speedup over autoregressive decoding on MoE models.
arXiv:2607.14246v1 Announce Type: new
Abstract: Generative models are steered with knobs -- prompts, guidance scales, property tags. Turn one as hard as you like and, past a point, it stops moving the property you care about. We find that ceiling is not a shortcoming of the model but a budget, set by the training data before the model is trained: a property's movable range splits in two -- the part a knob can reach, and a second, significant part that only examples -- concrete instances of what you want more of -- can reach. That second part is usually much larger, but not always, and the same budget says so in advance.
Reaching that second part takes a different move: instead of turning a knob, you show the model examples, composed from what it already learned rather than added to its training. A cheap audit of the training data measures the budget; we give a recipe for building the example set that reaches all of it.
This buys two things a knob can't. Reach: it moves a property across the whole budget, not just the part a knob reaches. Expressiveness: it steers toward targets you can only specify by example -- including ones you can't put into words. We turn these into a handful of falsifiable claims and verify them in two unrelated domains, image and crystal-structure generation -- marking where a knob is enough, and where only examples will do.
arXiv:2607.14651v1 Announce Type: new
Abstract: Persistent external memory enhances agent continuity but introduces persistent security vulnerabilities: adversarial content can be injected via standard interaction channels, retained across turns, and later distort downstream behavior. To address this challenge, we propose MemPoison, a comprehensive benchmark and analysis framework featuring 1227 hand-validated cases across four attack types, three injection channels, and three representative memory substrates, evaluated on seven open-weight and three closed-weight model families. We introduce a three-tier taxonomy: (L1) direct single-record corruption, (L2) compositional multi-record corruption and (L3) context-triggered dormant corruption. Our evaluations reveal a distinct defense frontier: while baseline write-time defenses, such as consistency checks, substantially suppress direct L1 attacks, they fail to reliably suppress L2 and L3 attacks. Through mechanistic influence decomposition (MID), we demonstrate structural blind spots in write-time defenses, which admit seemingly benign records that later become harmful through joint retrieval composition or trigger-conditioned activation. Our findings advocate for shifting from static filtering to adaptive, context-sensitive memory defense strategies.
arXiv:2607.14652v1 Announce Type: new
Abstract: Topology optimisation (TO) often requires repeated finite element analysis and sensitivity-based material updates, which can be costly when multiple candidate designs are needed under varying physical and design conditions. Generative TO offers a route to rapid design exploration, but existing models may rely on adversarial training, long reverse-diffusion sampling, or external guidance to maintain structural feasibility and physical consistency. This study develops a flow matching-based topology optimisation (FMTO) framework for conditional topology generation. Linear FMTO is first formulated as an endpoint-based baseline by interpolating between a Gaussian source field and the BESO reference topology. To introduce mechanically meaningful intermediate states, a trajectory-aware FMTO formulation is proposed, where volume-fraction-indexed BESO states are used to construct the probability path and target velocity field. This incorporates physics-guided optimisation history into generative flow learning without adding inference-time optimisation. A path--velocity mismatch analysis explains why moderate trajectory weighting can improve generation stability, whereas excessive guidance may over-constrain the learned transport. Numerical examples show that FMTO generates diverse topology candidates with improved compliance-related performance, volume-fraction satisfaction, topology fidelity, and substantially fewer sampling steps than a diffusion-based baseline. Under limited training data, trajectory-aware FMTO achieves the best overall performance with a moderate trajectory weight. Studies on trajectory-anchor density and three-dimensional topology generation further demonstrate the influence of path design and the applicability of the proposed framework beyond two-dimensional problems.
arXiv:2607.14247v1 Announce Type: new
Abstract: Incremental redundancy (IR) can reduce error rates by spreading coded bits across multiple transmission attempts. However, conventional stop-and-wait operation with coarse feedback often over-provisions retransmissions, triggers unnecessary decoding attempts, and increases end-to-end latency. This paper develops enhanced feedback and scheduling mechanisms that predict the additional redundancy needed for successful decoding and allocate only the required resources. We study two complementary strategies. First, using channel statistics, we learn a one- or two-shot mapping from channel quality to the minimum redundancy budget. As a byproduct, we derive an achievable reliability lower bound on the error probability of hybrid automatic repeat request (HARQ) systems. Numerical results with polar-coded IR-HARQ scheme show that the bound can be closely approached by appropriately selecting the second-transmission redundancy over a wide SNR range with savings up to 60\% in retransmission size. Second, we propose a realization-aware early-feedback mechanism that uses first-transmission reliability information to make per-codeword decisions before decoding: whether the codeword is already decodable, if not, how many additional redundancy versions are needed, or whether decoding is unlikely and rate adaptation is preferable. Link-level simulations with 5G NR LDPC codes show that both predictors achieve high accuracy (about 96\% in our study), increasing the probability of successful decoding within at most two transmission occasions.
arXiv:2607.14248v1 Announce Type: new
Abstract: Lane boundary detection is a critical component in autonomous driving systems and has been rigorously studied in regular driving scenarios. However, it is less explored in vehicle racing, where the car moves at higher speeds across more extreme road geometries. To study this problem, we introduce a new dataset for 3D lane detection in racing, featuring >$250$k images from multiple camera feeds and inertial measurements taken with a Lexus LC 500 driving on a closed circuit. With this dataset, we compare various approaches to 3D lane detection and propose modifications that permit frames to be processed at rates of almost 300Hz while retaining high predictive performance in the racing application. This facilitates a multi-camera ensemble approach that is validated on hardware. We show that sensing modalities such as inertial measurements can be leveraged for pre-integration to regress road geometries over both cameras and time, yielding improvements in key metrics. Compared to methods such as BevLaneDet, adding odometry and ensemble predictions improves the F1 score by 3 points and reduces near-vehicle mean absolute errors (MAEs) by $>30 \%$. We show F1 scores $>$0.9 and lateral MAEs of $<$0.18m in vehicle deployments.
arXiv:2607.14350v1 Announce Type: new
Abstract: Fine-grained manipulation recognition requires modeling evolving relations among hands, objects, tools, and supporting surfaces. Conventional graph-based methods use pairwise edges that can fragment a coordinated event into disconnected binary relations. We propose a dynamic manipulation hypergraph framework that represents multi-entity configurations as higher-order relational units. At each temporal step, relevant entities are encoded using appearance, spatial, motion, and semantic-role features. Hyperedge candidates are instantiated and ranked using proximity, contact, and motion-coupling predicates. A hypergraph reasoning network performs node-to-hyperedge and hyperedge-to-node message passing, followed by temporal attention over the evolving interaction structure. The framework provides class-agnostic hyperedge-importance scores that identify entity configurations and temporal intervals emphasized by the model without treating them as causal explanations. Quantitative evaluation is conducted on EPIC-KITCHENS-100/VISOR and Assembly101 under an annotation-assisted entity-localization protocol. Video-only and entity-based methods provide contextual comparisons, while a matched pairwise graph and a static hypergraph serve as the principal controlled baselines because they use identical entity inputs and comparable relational settings. The proposed method improves HO-F1 over the matched pairwise graph by 6.9 percentage points on EPIC-KITCHENS-100/VISOR and 9.5 points on Assembly101, and exceeds the static hypergraph by 4.4 and 5.8 points, respectively. Qualitative analysis on ARCTIC further shows correspondence between highly ranked hyperedges and contact-rich manipulation intervals. These results demonstrate the value of time-varying higher-order relational modeling for fine-grained manipulation activity recognition.
arXiv:2607.14655v1 Announce Type: new
Abstract: Online brain-computer interface research requires software that can acquire multimodal physiological data, train and update decoders, run live inference, and preserve the full experimental provenance in a reproducible workflow. We present Dendrite, a real-time brain-computer interface application in Python that brings signal acquisition, decoder training, and live inference together in a single, ready-to-run application that stays modifiable. Dendrite records several signal streams at once, each at its native rate, and executes multiple processing modes concurrently against them. A decoder can start from a previously trained model or be fit mid-session while the pipeline keeps running, and the same recordings feed offline training in the same application. Each recording, decoder, and training run is tracked in a database, and every decoder records the configuration and the source recordings it was trained from, so a deployed decoder traces back to what produced it. The experimental paradigm stays external, an independent program in any language that reaches Dendrite over the network, rather than a module built inside the runtime. We validate the full system end-to-end on in-house and public BCI datasets, training and updating decoders online while the pipeline runs in real time. Dendrite is open-source under the GPL-3.0 license at https://github.com/dendrite-bci/dendrite. The result is a reproducible, open-source biomedical-computing system for developing and evaluating online BCI paradigms.
arXiv:2607.14249v1 Announce Type: new
Abstract: Mobile usage traces are critical for tasks such as user behavior prediction and app recommendation, yet their use is constrained by privacy restrictions and costly large-scale data collection. Although generative models perform well on general time series, their application to mobile usage data remains challenging because (i) limited user activity causes severe sparsity, (ii) heterogeneous variable types complicate joint modeling, and (iii) functional differences across apps create pronounced usage imbalance. To address these challenges, we propose Multivariate-Imaging Diffusion (MIDiff), a diffusion-based framework operating in an imaging space defined by Cross-Gramian Angular Sum Field (C-GASF). C-GASF transforms sparse multivariate sequences into correlation images, while MIDiff employs Triple Attention in a U-Net to preserve temporal consistency and variable dependencies. Experiments show that MIDiff achieves state-of-the-art performance across fidelity metrics. In particular, it obtains a Discriminative Accuracy (DA) of 0.1526, compared with 0.3476 for the strongest baseline, ZITS-VAE, demonstrating its effectiveness in generating realistic and diverse mobile usage traces. Our code is available at https://github.com/YilaiLiu-HKU/MIDiff.
arXiv:2607.14413v1 Announce Type: new
Abstract: We prove that every randomized synchronous Byzantine Agreement protocol in the full-information, strongly adaptive adversary model, secure against $t$ corrupt parties, has worst-case expected round complexity \[
\Omega\!\left(\frac{t^2}{n\log(n+1)}\right). \] This improves upon the seminal $\Omega(\frac{t}{\sqrt{n\log n}})$ bound of [Bar-Joseph, Ben-Or 98]. Our result matches the recent upper bound of $O\left(\min\left\{\frac{t^2\log n}{n},\frac{t}{\log n}\right\}\right)$ of [Dufoulon, Pandurangan 25], up to a $\log^2 n$ factor in the $t\ll n$ regime. Our proof takes inspiration from the recent works of [Etesami, Mahloujifar, Mahmoody 20] and [Haitner, Karidi-Heller 26]. Specifically, we prove a multi-round concentration lemma showing that any transcript event of probability $p$ can be forced with probability one by corrupting $O(\sqrt{n\log(\frac1p)})$ parties in expectation. From there, tools from [Chor, Merritt, Shmoys 89] allow us to lower-bound the probability of the protocol not concluding in $R$ rounds by $\frac{1}{n^{O(R)}}$, using a crash schedule involving at most $R$ parties. The combination of these techniques yields the desired bound.
arXiv:2607.14657v1 Announce Type: new
Abstract: We advocate for AI/ML issue resolution frameworks tailored to maintenance workflows and the nature of modern AI/ML systems. Existing issue resolution frameworks largely emerged for traditional software maintenance practices and do not explicitly account for characteristics common in AI/ML systems, such as stochastic behavior, experimentation-driven workflows, and heterogeneous artifacts beyond source code. To identify the unique characteristics of issue resolution in AI/ML systems and motivate the need for tailored frameworks, we conducted a qualitative study of issue resolution workflows documented in 100 issue reports and pull requests across four widely used AI/ML systems: TensorFlow, scikit-learn, MLflow, and AutoGPT. Our findings suggest that issue resolution in AI/ML systems involves: recurring AI/ML-related activities that span multiple resolution stages; iterative experimentation and adaptive verification; and coordinated changes across artifacts such as datasets, prompts, and model configurations. We also observed challenges related to reproducibility, nondeterministic behavior, and artifact coordination. Building on these findings, we present a vision for AI/ML issue resolution frameworks and discuss research directions and tooling support needed to realize this vision.
arXiv:2607.14658v1 Announce Type: new
Abstract: While Multimodal Large Language Models (MLLMs) excel in general tasks, rigorous scientific reasoning remains challenging due to the limitations of monolithic, linear planning. Such sequential designs often suffer from visual-semantic misalignment, long-context hallucinations, and brittle execution under fixed task granularity. We propose TopoAgent, a self-evolving topological framework that replaces linear trajectories with dynamic, state-isolated graph evolution. TopoAgent first employs a front-end decomposer to fracture complex queries into visually-grounded atoms. These atoms are organized into a Directed Acyclic Graph (DAG) based on their dependencies, enabling strict context isolation to shield the reasoning engine from irrelevant historical noise. Furthermore, we introduce adaptive atomic fission, which dynamically splits bottleneck nodes into finer-grained sub-atoms at runtime when tool capability boundaries are exceeded. Extensive experiments across mathematics, physics, and chemistry benchmarks demonstrate that TopoAgent significantly outperforms state-of-the-art linear agent frameworks, providing a robust, noise-resistant, and self-correcting paradigm for autonomous scientific reasoning.
arXiv:2607.14661v1 Announce Type: new
Abstract: Deploying large language models (LLMs) as personal assistants on mobile devices demands privacy, low latency, and offline availability, yet the computational cost of giant models clashes with strict edge-hardware budgets. We argue that this tension cannot be resolved by model compression alone; it requires decomposing on-device intelligence into complementary functional roles. We present SmartRAG, a fully on-device framework that organizes an intelligent assistant around four coordinated modules -- Perception, Memory, Focus, and Thinking. At the core of SmartRAG is EvoNER, a continually learnable named-entity recognizer that incrementally expands its label inventory through teacher-distilled updates, enabling the system to absorb previously unseen entity types without retraining the backbone LLM. Extracted knowledge is stored in MRGraph, a three-layer provenance-preserving knowledge graph, and retrieved at query time through a hybrid pipeline combining graph traversal, lexical matching, and dense semantic search. The on-device LLM is invoked only for high-value semantic operations -- labeling, planning, and answer synthesis -- keeping inference costs bounded. Experiments on four QA benchmarks (TriviaQA, Natural Questions, HotpotQA, MultiHopQA) show that SmartRAG with a quantized 1.7B-parameter backbone achieves multi-hop reasoning performance competitive with models up to 18$\times$ larger, while running entirely on commodity smartphones within practical memory and latency envelopes.
arXiv:2607.14664v1 Announce Type: new
Abstract: Epigenetic changes -- heritable, long-lived, yet actively reversible modifications of the chromatin state -- display memory, threshold activation and hysteresis, features that are the hallmark of rate-independent dissipative evolution. We propose a mathematical framework, Rate-Independent Epigenetics, that models epigenetic change within the theory of rate-independent systems and is consistent with two fundamental principles identified with the laws of thermodynamics. In this framework, a model is specified by a state space of epigenetic configurations, a stored-energy functional depending on the state and on an external loading, and a 1-homogeneous dissipation potential encoding the resistance of the epigenetic machinery to change. Assuming an energetic evolution principle, the governing equations follow, with no further modelling hypotheses. The energy balance is exact energy conservation, and the 1-homogeneity of the dissipation potential forces a non-negative, minimal (economical) dissipation. Under natural coercivity and continuity assumptions we establish existence of energetic solutions and, via vanishing viscosity, of balanced-viscosity solutions that resolve the ambiguity of the energetic formulation at epigenetic switches; uniqueness holds under convexity and, in the scalar case, under a mild finite-multiplicity condition. We then build a variational time integrator, prove its convergence to energetic solutions and a global energy-consistency estimate. The framework is illustrated on the scalar linear play operator, on an example with a double-well energetic potential, showing the ability of the framework to study multi-stability scenarios and catastrophic switches and on a nonlinear problem, proving that the theoretical results hold. The presented framework can be seen as a skeleton for a richer thermodynamically-consistent theory incorporating viscous dissipation features.
arXiv:2607.14665v1 Announce Type: new
Abstract: Physics-informed neural networks (PINNs) offer a flexible framework for solving partial differential equations (PDEs), but training can become computationally expensive when a large number of collocation points are required to accurately enforce the governing equations. To alleviate this cost, we introduce multigrid-based parameter-updated PINNs (MPU-PINNs), a coarse-to-fine training strategy that progressively increases the number of training points throughout the learning process. The proposed approach begins by training a neural network on a coarse set of collocation points and then transfers the learned parameters to successively finer levels. This initialization strategy enables the network to capture the global features of the solution at a relatively low computational cost before refining local details with additional training points. To further improve performance for high-frequency problems, we incorporate a scaling technique that mitigates the effects of spectral bias during training. We evaluate MPU-PINNs on several benchmark PDEs, including two- and three-dimensional Poisson equations, a convection-diffusion-reaction equation, and the Helmholtz equation. Numerical experiments indicate that MPU-PINNs greatly reduce training time while achieving accuracy comparable to that of conventional PINNs and other representative variants such as SA-PINNs and XPINNs. The results further suggest that the proposed coarse-to-fine learning strategy substantially decreases the optimization effort required at finer levels. Overall, MPU-PINNs provide an efficient single-network training framework that enhances the computational efficiency and scalability of PINNs for a broad range of PDE problems.
arXiv:2607.14666v1 Announce Type: new
Abstract: Identification (ID) coding, introduced by Ahlswede and Dueck, extends Shannon's classical communication paradigm by replacing message reconstruction with hypothesis testing. Instead of decoding the transmitted message, the receiver only decides whether a particular message was sent. A fundamental result of ID theory is the double-exponential growth in the number of identifiable messages with respect to (w.r.t.) the blocklength. This scaling behavior enables fundamentally new communication architectures for large-scale distributed systems and forms a key building block of post-Shannon communication.
While ID cannot replace classical communication in general, it is particularly well-suited for scenarios in which full message reconstruction is unnecessary, such as monitoring, alarming, and control systems.
In this survey, we review the theoretical foundations of ID coding and discuss emerging communication architectures and application domains based on this paradigm. Particular emphasis is placed on practical use cases, including monitoring systems, special-purpose data storage, joint identification and sensing (JIDAS), semantic communications, mobile-network control systems and networked consensus testing systems. We further highlight recent system concepts, industrial perspectives, and implementation examples that illustrate how ID-based principles can be realized in practical communication systems.
arXiv:2607.14131v1 Announce Type: new
Abstract: Urdu fake news detection remains under-resourced despite Urdu being spoken by over 231 million people worldwide. While prior work has demonstrated strong in-domain performance on individual Urdu datasets, cross-dataset generalisation has received little systematic attention. This paper presents the first cross-dataset generalisation study for Urdu fake news detection, using two publicly available balanced datasets: the Ax-to-Grind Urdu corpus (10,083 articles, 15 domains) and the Notri-Fact Urdu dataset (13,388 articles). We fine-tune xlm-roberta-base under four experimental conditions, in-domain on each dataset and two zero-shot cross-domain transfer directions, comparing against TF-IDF baselines using Logistic Regression and Support Vector Machines. Our experiments reveal a striking asymmetry: Notri-Fact to Ax-to-Grind transfer achieves a macro F1 of 0.771, while the reverse collapses to F1 of 0.005, with the model predicting fake for 99.7% of test articles. We demonstrate that this collapse stems from a systematic length confound in Ax-to-Grind, where fake articles average 117 words versus 35 for real articles, a 3.4x asymmetry inducing shortcut learning. A length ablation capping articles at 50 words yields only a 0.0067 F1 drop, confirming the confound inflates but does not solely drive in-domain performance. We provide a reusable diagnostic methodology that combines bidirectional transfer analysis and prediction-collapse inspection to identify confound-driven behavior in multilingual fake news detection settings.
arXiv:2607.14672v1 Announce Type: new
Abstract: Continuous-time spiking neural networks (SNNs) provide an event-driven framework for temporal computation, computational neuroscience, and neuromorphic hardware. However, training deep continuous-time SNNs is severely constrained by the memory required for exact spike-time computation, which evaluates and retains candidate firing times over intervals determined by presynaptic spike ordering. Here we introduce a memory-efficient training framework based on differentiable spike-time discretization (DSTD) for leaky integrate-and-fire neurons with general membrane and synaptic time constants. DSTD maps irregular presynaptic spikes onto differentiable weighted events at fixed time points, replacing the input-dependent candidate dimension with $M$ fixed time intervals while accurately approximating continuous-time membrane-potential dynamics. This reduces candidate-related activation memory from $O(N_{\mathrm{out}}N_{\mathrm{in}})$ to $O(N_{\mathrm{out}}M)$ in the case of time-to-first-spike (TTFS) coding, where $N_{\mathrm{in}}$ and $N_{\mathrm{out}}$ denote the numbers of presynaptic and postsynaptic neurons, respectively. We further introduce synfire-chain-inspired temporal regularization that organizes layer-wise firing windows, mitigates dead-neuron failures, and enables pipeline-like processing. In dense LIF layers, DSTD reduced peak memory consumption by up to approximately 100-fold and training time by up to approximately 20-fold compared with exact spike-time computation. Together, these methods allowed us to train 9-layer convolutional SNNs on CIFAR-10 and 20-layer convolutional SNNs on Fashion-MNIST on a single GPU.
arXiv:2607.14673v1 Announce Type: new
Abstract: Evaluations (Evals) are a deployment bottleneck for real-world AI applications: public benchmarks rarely match a team's users, context, or policies, and human review is often tedious to scale. Motivated by our work with AI applications in the public sector, this project addresses recurring evaluation challenges encountered when applications must satisfy local policy and governance requirements. We present Kaleidoscope, an integrated workflow for contextual functional evaluation that links persona-based test generation, contextualized rubrics, and human review for reliability-gated automated scoring. Generated test cases are scored against application-specific rubrics; human annotations provide reviewable labels; and LLM judges automate scoring only when their agreement with those labels meets a configured threshold. Kaleidoscope is therefore a practical, inspectable, iterative workflow for product teams. We report early evidence from a three-week pilot across four organizational use cases and custom-rubric judge experiments on 108 annotated Q\&A pairs spanning four domains and 14 evaluation dimensions. The results highlight useful features for end-to-end reliable, automated scoring.
arXiv:2607.14675v1 Announce Type: new
Abstract: Robust human-robot interaction in complex environments requires accurate gesture perception, semantic scene understanding, and reliable task planning under limited onboard computing resources. This paper presents a cloud-edge multimodal interaction framework that integrates an enhanced YOLO-based gesture detector with coordinated large language model (LLM) and vision-language model (VLM) agents. The proposed detector, incorporates the Convolutional Block Attention Module (CBAM) into the neck and replaces the baseline bounding-box regression objective with Distance-IoU (DIoU) loss. These modifications improve feature discrimination and localization for small or partially occluded gestures in complex backgrounds. The cloud layer performs gesture detection, scene understanding, multimodal fusion, and action planning, whereas the TonyPi robot locally handles data acquisition, communication, action execution, and feedback. Experiments on a public gesture dataset and a custom dataset show that YOLO-DC achieves precision values of 98.9% and 95.0%, with mAP@0.5 values of 90.7% and 92.7%, respectively. System-level evaluation yields success rates of 95%, 88%, and 82% for single-action, composite-action, and vision-dependent tasks. A 30 participant evaluation yields an overall mean satisfaction score of 3.69 out of 5. These results demonstrate the feasibility of combining refined gesture detection with multimodal agents for resource-constrained robotic interaction.
arXiv:2607.14676v1 Announce Type: new
Abstract: A variable-to-variable (V2V) length code parses a source sequence into phrases of variable length and maps each phrase to a binary codeword of, generally, a different random length. After encoding $n$ phrases, the realized compression ratio $R_n=\Lambda_n/\Sigma_n$ -- total codeword length over total source-symbol count -- is the finite-sample counterpart of the code's asymptotic rate $\rho$, to which it converges only as $n\to\infty$. This paper first derives exact formulas for all integer moments of $R_n$ for a given discrete memoryless source (DMS). Specifically, we obtain a closed-form formula for every moment $\E\{R_n^k\}$ as a one-dimensional integral involving only single-phrase moment generating functions of the pair $(L,\ell)$ -- the phrase length, in source symbols, and codeword length, in bits. From these moments we derive an Edgeworth approximation to the cumulative distribution function (CDF) of $R_n$ that is substantially more accurate than the central limit theorem (CLT) approximation. Using the Laplace method of integration, we also derive explicit closed-form formulas for the bias constant $C=\lim_{n\to\infty}n(\E\{R_n\}-\rho)$ and for the variance constant $\lim_{n\to\infty}n\cdot\Var\{R_n\}$. The analysis extends to Markov sources via state-indexed matrices with a redundancy formula obtained in closed form. On the coding-theoretic side, we cast V2V length codes as finite-state encoders and apply a generalized Kraft inequality for a compression-rate lower bound, and give a structural decomposition of the bias coefficient that separates cleanly across variable-to-fixed (V2F) length codes, fixed-to-variable (F2V) length codes, and V2V length codes. Applied to the Khodak code of Bugeaud, Drmota, and Szpankowski, this decomposition shows that its improved performance is reflected in its smaller bias constant.
arXiv:2607.14375v1 Announce Type: new
Abstract: We study exact verification of ReLU networks in an adversarial smoothed model. Every network weight and bias is independently perturbed by Gaussian noise, clipped to $[-2,2]$, and rounded to the exact dyadic grid determined by the input bit complexity. We show that, under the standard assumption $\mathrm{NP}\not\subseteq\mathrm{BPP}$, there is no sound and complete verifier whose expected running time is polynomial in network size, bit complexity, and inverse noise level for every base instance. The conclusion already holds at the fixed noise level $\sigma_\star=2^{-11}$ for one-hidden-layer networks over a unit box, with hidden fan-in at most three and base coefficients in $[-1,1]$.
The proof combines an exact gap embedding with a quantitative robustness argument. For every E3SAT formula $\Phi$ with $m$ clauses, a four-ReLU-per-clause construction satisfies $\max_{x\in[0,1]^n} g_\Phi(x)=(m-\operatorname{unsat}(\Phi))/3$, and coordinatewise threshold rounding never decreases the objective. A weighted parameter-sensitivity inequality and Gaussian concentration then show that a verification gap linear in $m$ survives the aggregate perturbation of all coefficients with probability at least $1-e^{-m/8}$. The proof includes clipping, exact dyadic rounding, output-layer perturbations, polynomial-bit sampling of the rounded Gaussian law, and the conversion from expected smoothed running time to a BPP algorithm. Computational checks test the exact identity and illustrate the different scaling of extensive and constant gaps; they are diagnostics rather than evidence for the complexity theorem. The result concerns worst-case base networks in the stated absolute-noise model, but it shows that parameter nondegeneracy alone does not yield a universal smoothed-polynomial guarantee for exact verification.