Search arXiv⌕ Search

arXiv subjects

Search papers

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

At least 1,045 records · Page 58Linked to original sources
arXiv2026

Evaluating and Improving Static Application Security Testing Tools for Rust

Rust has become a popular systems programming language in recent years because of its strong guarantees on memory and concurrency safety. Many types of system software have been re-implemented in Rust. However, Rust programs can still suffer from common memory and concurrency vulnerabilities due to unsafe code and misunderstandings of its complex mechanisms. To mitigate such vulnerabilities, developers often rely on static application security testing (SAST) tools. However, the effectiveness of existing Rust SAST tools on real-world vulnerabilities remains underexplored. In this paper, we first conduct an empirical evaluation of mainstream Rust SAST tools using security vulnerabilities identified in real-world Rust applications. We systematically assess their effectiveness, uncover common weaknesses, and analyze the root causes behind them. Motivated by the study, we propose TRUST, a large language model (LLM)-assisted automated testing framework. TRUST automatically analyzes the official Rust reference to derive and implement semantics-preserving transformations. It leverages these transformations to generate mutant programs for evaluating Rust SAST tools and uncovering potential faults within them. Overall, TRUST has revealed 46 faults across six popular SAST tools, 17 of which have been confirmed. In addition, our study yields ten empirical findings and four practical lessons that provide actionable guidance for developing more effective, robust, and maintainable Rust SAST tools.

cs.CR↗
arXiv2026

From Optical Flow to Safety: Visual Safety Certification via Scale-Free Relative Motion

Safe autonomous navigation using monocular vision remains challenging because explicit obstacle states are not directly observable. This letter introduces a visual safety-certification paradigm that uses scale-free, depth-normalized relative motion encoded by monocular optical flow as the representation for collision-risk certification, without reconstructing obstacle position, velocity, geometry, or a metric world model. Unlike conventional optical-flow-based navigation approaches that rely on image motion to shape avoidance behavior, the proposed framework directly encodes collision-cone geometry and safety constraints in this relative-motion representation. An online Concurrent Learning observer estimates the normalized relative velocity and provides a computable estimation-error bound. This uncertainty is propagated into the collision cone through angular inflation and a monocular robot-footprint margin, yielding a Robust Vision-Based Collision Cone Control Barrier Function (RV-C$^3$BF). An optimal-decay CBF quadratic program minimally modifies the nominal control input to enforce the resulting robust safety constraint under the stated assumptions. Extensive simulation and real-world experiments on a TurtleBot3 in cluttered environments with static and dynamic obstacles demonstrate collision avoidance using only monocular vision and onboard proprioception, with the estimation-error bound containing the measured error in $98.3\%$ of simulation samples and the robot achieving collision-free navigation in $93$ of $100$ real-world trials.

cs.RO↗
arXiv2026

Memorilla: Latent Semantic Memory for LLMs

Memory enables large language models (LLMs) to use information beyond their parameters, such as past user conversations, long documents, or an agent's earlier actions. For a frozen LLM, access to this accumulated knowledge is limited to what a memory system places in its context window. However, gathering and combining relevant information needed for each query while keeping the model's context short remains challenging for existing systems. Here we introduce Memorilla, a memory system that gathers information from an entire document collection into a fixed number of query-dependent 'memory tokens' for a frozen LLM. Memorilla encodes documents (such as user chats, book chapters) once into reusable embeddings, then learns to retrieve and place query-specific information in the LLM's input embedding space. Using only 16 memory tokens, Memorilla achieves the best performance against baselines including Mem0 and MemoRAG on five of eight benchmarks spanning personalization, long-document and knowledge-intensive question answering. Notably, on FactKG, it reaches 84.33% accuracy versus 80.43% with full-context inference, while using 108x fewer tokens to represent the source documents. Furthermore, Memorilla can facilitate continual learning in agentic systems where the document count (the agent's past turns) increases throughout the trajectory. In a TextWorld environment, we show that Memorilla reduces the agent's tendency to wander between rooms it has already explored, and improves its average success rate from 18.6% with full-history in-context learning to 24.2%. Overall, Memorilla aids frozen LLMs in accumulating and using knowledge effectively across long-context interactions and takes a step towards building continually learning AI systems.

cs.LG↗
arXiv2026

Does Compression Imply Generalization? A Minimum Description Length Perspective

A central question in modern learning theory is what notion of compression, if any, explains why over-parameterized neural networks generalize. Existing answers measure complexity at different levels, ranging from weights to representations; however, estimating the associated quantities either requires held-out data in principle or relies on the challenging (ultra) high-dimensional mutual information estimation. To overcome these challenges, we approach the question through the minimum description length (MDL) principle, and specifically, we propose the prequential regret as a complementary signal that is computable from the training trajectory alone. We establish that, in the (nearly) interpolating regime, the expected prequential regret upper-bounds the description length of the trained parameter under the algorithm-induced distribution, and that this description length translates into a high-probability generalization bound in the PAC-MDL setting. Along the way, we show that the encoder-complexity correction recently added to the algorithm-level information bottleneck (IB) is upper-bounded by an MDL parameter description length, \new{bringing together} the two views of compression from MDL and IB. Empirically, the prequential regret tracks the generalization error on CIFAR-10 and CIFAR-100, with Pearson correlations exceeding 0.9.

cs.LG↗
arXiv2026

Observability as a constraint qualification for a nonsmooth bilevel PDE-constrained problem

Motivated by experiment design for parameter identification in image reconstruction, we analyze a bilevel control problem involving sparse inversion at the lower level. Qualified optimality conditions in explicit multiplier form are shown to hold under either an observability condition for a coupled system or the Lebesgue nullity of a contact set induced by the lower-level adjoint variable. We prove that these conditions are independent of one another and that they cannot, in general, both be omitted. The approach is based on the characterization of local first-order geometric objects (tangent and normal cones) associated with a set of lifted constraints. Based on the resulting optimality conditions, we formulate a reduced gradient method and illustrate it through numerical experiments.

math.OC↗
arXiv2026

DPA-MoE: A Runtime Precision Control Framework for MoE Inference

Mixture-of-Experts (MoE) models reduce computation by routing each token to a small set of experts, but each selected expert is still used at a fixed precision. We present DPA-MoE, a runtime precision control framework that makes routed experts any-precision. DPA-MoE encodes expert feed-forward weights as prefix-decodable chunks using SharedScale AnyBCQ, profiles per-expert reconstruction residuals offline, and allocates chunks at inference time using live router gate scores. This post-routing allocation lets a single encoded MoE checkpoint operate at multiple effective weight budgets without retraining or re-encoding. Experiments on Qwen3-30B-A3B and DeepSeekMoE-16B show that DPA-MoE improves KL divergence and downstream accuracy over uniform chunk allocation at matched budgets, with modest steady-state throughput overhead in our prototype.

cs.CL↗
arXiv2026

Model Checking HyperRecHML is Decidable

Temporal hyperlogics combine explicit quantification over traces with temporal requirements evaluated over the quantified traces. HyperRecHML is a temporal hyperlogic which allows for arbitrary mixing of trace quantification and the use of fixed points for expressing temporal requirements, which makes it very expressive in comparison to other first-order hyperlogics. HyperRecHML has already been successfully applied in runtime verification, but the decidability of its model checking problem remains open. We answer this question positively by providing two main contributions. Firstly, a normalization procedure that allows to reduce arbitrary HyperRecHML formulas to a normal form with restricted nesting of trace quantification and fixed points. Secondly, we provide an automata-based model checking algorithm for formulas of this normal form. The complexity of our algorithm is comparable to similar ones for other hyperlogics, despite the extra expressive power.

cs.LO↗
arXiv2026

Perception or Reasoning? Diagnosing and Tackling Reinforcement Learning Bottlenecks in VLMs

Reinforcement learning has brought strong gains to language model reasoning, but its improvements on visual tasks remain less consistent. One difficulty is that visual task failures can arise from different sources: the same benchmark may be limited by perception for one model and by reasoning for another. We introduce Perception and Reasoning Attribution (PARA), which measures the remaining perceptual and reasoning headroom of each model--benchmark pair by comparing how many current errors are recovered with more accurate visual information versus a stronger reasoner. Across 4 vision-language models and 17 multimodal benchmarks, PARA broadly agrees with the expected characteristics of existing benchmarks while revealing substantial model-specific variation. More importantly, it shows that RL gains become smaller as perceptual headroom increases, but larger when reasoning explains more of the recoverable errors, suggesting that current RL exploits reasoning headroom more effectively than perceptual headroom. Motivated by this gap, we analyze how existing RL objectives affect visual perception and find that reward- and token-level signals influence visual attention only indirectly. We therefore propose GRAD, a group-relative attention distillation objective that uses the best rollout in each group to directly guide the visual attention of weaker rollouts. GRAD consistently improves performance across two model scales and seven benchmarks, and further complements existing RL methods.

cs.CV↗
arXiv2026

Optimally large cuts in both directions

We prove that for every integer $d\ge2$ and all sufficiently large $m$, every digraph with $m$ edges and minimum outdegree at least $d$ has a vertex bipartition for which each directed cut is of size at least \[\left\lceil\frac{d-1}{2(2d-1)}m+\frac{d^2}{2(2d-1)}\right\rceil.\] The bound is sharp for infinitely many $m$. This answers for large graphs a question of Scott and proves a conjecture of Lee, Loh, and Sudakov. For $d=2$ we prove that $\lceil m/6\rceil$ is achievable for all $m$. We also establish a stability result characterizing near-extremal graphs.

math.CO↗
arXiv2026

RDL-Bench: A Benchmark for Task-Aware Question Answering over Relational Databases

Relational databases (RDBs) remain the primary infrastructure for storing and managing structured data across enterprise and scientific domains. Natural-language (NL) interfaces to RDBs aim to let users ask questions without writing SQL, but real user needs go beyond SQL-style lookup: some questions require reasoning over the observable database state, while others require predictive inference from historical relational records under temporal constraints. Existing benchmarks address these goals in isolation. To address this gap, we introduce RDL-Bench, a benchmark for task-aware question answering (QA) over real RDBs. RDL-Bench organizes diverse user questions into reasoning-oriented questions, whose answers are determined by the current database state, and prediction-oriented questions, whose answers depend on future outcomes under temporal constraints. Each instance contains an NL question, task metadata, schema information, temporal context, either executable evidence or target-construction logic, and denotation-level ground truth. RDL-Bench supports two evaluation settings: native solvers under their intended capabilities, and task-aware modular systems where a router dispatches each question to an appropriate execution module.

cs.LG↗
arXiv2026

Calibration Language Shapes Block-Influence Pruning in Multilingual Language Models

Block Influence (BI) ranks Transformer blocks for depth pruning from their input-output cosine change, but the ranking depends on the calibration distribution. We study whether English calibration transfers to Indian languages in Qwen2.5-1.5B-Instruct, Llama-3.2-1B, and Gemma-2-2B. English, Hindi, Marathi, and Tamil use disjoint Wikipedia articles for calibration and evaluation; every selector receives the same 150-chunk budget, and Tamil is excluded from multilingual aggregation to test cross-script transfer. Across all three models, late-block BI is 20.7-55.5% higher for the three Indian languages than for English, and every predeclared late-minus-middle contrast has a 95% bootstrap interval above zero. This mismatch changes the low-BI blocks selected for removal despite high global rank correlations. Averaging BI over equal English, Hindi, and Marathi budgets mitigates the resulting perplexity damage for Qwen at six removed blocks and for Gemma at all tested depths, including held-out Tamil. The mitigation is not universal: on Llama, balancing improves Hindi and Marathi at two removed blocks but severely harms Tamil, while larger pruning budgets select the same blocks and collapse perplexity regardless of calibration. Rank-mean and minimax-rank aggregators do not dominate the raw mean. These results support a diagnostic claim rather than a universal pruning rule: English-only BI systematically misses late-layer activity for Indian-language text, but multilingual calibration must still be validated per architecture and pruning budget.

cs.CL↗
arXiv2026

Optimization of a Perturbed Implicit Sweeping Process by Constrained Discontinuous Controls

This paper studies optimal control problems governed by an implicit sweeping process with velocity-dependent constraint geometry, where the dynamics are described by a differential inclusion involving the normal cone to a moving convex polyhedral set. Such systems form a challenging class of nonsmooth differential inclusions due to the implicit coupling between the state, velocity, and constraint reaction. To address these difficulties, we use a method of discrete approximations together with tools of variational analysis and generalized differentiation. This approach allows us to derive necessary optimality conditions for local minimizer in discrete-time problems and subsequently pass to the limit to obtain optimality conditions for the original continuous-time system. The obtained results extend existing optimal control theory for sweeping processes to a class of implicit dynamical systems with state-and velocity-dependent constraints.

math.OC↗
arXiv2026

Top-Down Microarchitecture Analysis Without Causal Modelling Is Dangerous!

Top-Down Microarchitecture Analysis (TMA) is the standard for identifying CPU bottlenecks. However, TMA implicitly models performance via a single causal path: Workload(dataset, algorithm) => CPU(CPI) => System(Performance) (microarchitectural efficiency path). It overlooks two hidden causal paths: Workload(dataset, algorithm) => Instructions(Retired) => System(Performance) (algorithmic efficiency path) and Workload(dataset, algorithm) => Instructions(Retired) => CPU(CPI) => System(Performance) (microarchitecture-algorithm efficiency path). This causal blindness often misleads architects into futile hardware optimizations. To address this, we propose Causal Top-Down Microarchitecture Analysis (CTMA). Utilizing the object causal model, CTMA explicitly models these three causal paths among the workload, instructions, CPU, and system. We validate CTMA across Intel, AMD, and ARM platforms. Our experiments reveal counterintuitive insights: (1) CPI Profiling Blindness: Algorithmic instruction bloat can double elapsed time while the CPI profile remains frozen. (2) Over-Speculation Congestion: Throttling the Frontend paradoxically improves performance in pointer-chasing algorithms. (3) ILP Window Collapse: Extreme data topologies shift bottlenecks from Backend ROB capacity to Frontend fill-rate starvation. (4) Op-Cache SMT Overlap: Ultra-small footprints yield SMT speedups on Intel but cause severe thrashing on AMD. (5) "Ghost State" Artifact: Stale pipeline mitigations on Intel Xeon Gold 5120T artificially boost performance by 22.75% on SPEC CPU2017 and 42.2% on SPEC CPU2026. Based on this, we propose a dynamic speculation throttling mechanism.

cs.PF↗
arXiv2026

Stronger Spectral Bound for Clique Number

Given an integer $k$, deciding whether a graph has a clique of size $k$ is an NP-complete problem. Wilf's inequality provides a spectral lower bound for the clique number of a graph. Strengthening this bound, Elphick and Wocjan proposed a conjecture in 2018 using positive adjacency eigenvalues. In this paper, we present an infinite family of graphs for which the Elphick and Wocjan conjecture is true. We find a stronger spectral lower bound for the clique number for this family of graphs.

math.CO↗
arXiv2026

Fast-VLA: You Only Think Once for Robot Manipulation

Vision-language-action (VLA) policies commonly place a multi-billion-parameter model inside the feedback loop, repeatedly recomputing task context whenever they predict a new action chunk. Yet task understanding changes far more slowly than the robot state. We introduce Fast-VLA, which invokes a frozen 4B VLM once per episode to contextualize the instruction and initial views as fixed, multi-layer key-value task memory. During execution, a lightweight online actor fuses learned time- and arm-indexed queries with current visual and proprioceptive feedback to form action queries. These queries retrieve task context from the fixed memory and predict action chunks without re-running the foundation model. Fast-VLA achieves 92.46% and 92.40% success on RoboTwin 2.0 Clean and Randomized, and 95.95% and 79.11% on LIBERO and LIBERO-Plus evaluation. Against three continually conditioned baselines on the same hardware, it reduces RoboTwin amortized policy inference time by 10.9-17.1x and requires 1.22 GiB of post-prefill online resident memory. Task-memory swaps further show that the actor relies on episode-matched task memory. These results show that task context can be established once while closed-loop control remains responsive throughout execution. Project page: https://garfield-kh.github.io/FastVLA

cs.RO↗
arXiv2026

PriorityFEC: Deadline-Aware Streaming FEC for KV-Cache Handoff in Edge Multi-Agent Systems

Multi-agent large language model (LLM) systems are increasingly deployed at the edge to support complex tasks that require collaboration and information exchange among multiple agents. However, when task contexts are passed across agents, shared context that has already been processed by upstream agents often needs to be prefilled again, resulting in substantial redundant computation. Reusing an already prefilled key--value (KV) cache can avoid this recomputation, but requires the reusable KV state to be transferred across the network before the receiving agent can begin generation. Under strict time-to-first-token (TTFT) deadlines and unreliable edge links, delivering the complete KV cache may be infeasible, making it necessary to prioritize and protect the most valuable KV information within a limited transmission budget. This paper proposes PriorityFEC, a utility-aware KV-cache handoff scheme that jointly exploits model-side KV importance and transport-side reliability. PriorityFEC first constructs a utility-aware source stream by placing high-utility KV blocks at earlier transmission positions. It then protects the ordered stream using a feedback-adaptive Streaming Forward Erasure Correction (FEC) mechanism, which schedules repair packets according to receiver feedback before the TTFT deadline. We implement PriorityFEC on a distributed edge LLM serving prototype and evaluate it with Qwen2.5-7B-Instruct and Llama-3.1-8B-Instruct across multiple datasets. Results show that PriorityFEC achieves superior task quality over the compared transport schemes, with its advantages becoming particularly pronounced under stringent deadline constraints. These results demonstrate the importance of jointly optimizing KV-cache utility and deadline-aware transport reliability when reusable LLM state must be handed off across unreliable edge networks.

cs.NI↗
arXiv2026

NOCE-Net: Representation Learning for Battery Operational Context via Nested Sequence Modelling

Learning effective representations from battery operational history is essential for predictive health management and control-oriented applications. Existing approaches rely on response-dependent engineered features or short early-life windows, limiting generalisability and precluding use in prospective settings where future responses are unavailable. We propose NOCE-Net, a deep nested sequence model that learns control-enabling representations directly from raw cyclic operational or telemetric data. Our data pipeline, re-BatteryData, standardises heterogeneous aging datasets into semantically equivalent Full Equivalent Cycles (FECs) defined by absolute charge throughput, enabling end-to-end learning across diverse operational regimes. NOCE-Net combines multi-patch transformer encoders for intra-cycle dynamics with a GRU backbone for inter-cycle state evolution, operating on approximately $700$ batteries across ten public datasets spanning over $300$ operational profiles. In zero-shot evaluation on unseen battery chemistries and usage patterns, NOCE-Net achieves $13.7\%$ MAPE in voltage response prediction, outperforming strong long-sequence baselines by over $43\%$ while using $40 \times$ fewer parameters. Shape and component diagnostics of the learned hidden states reveal that the GRU's principal direction of evolution achieves Spearman $|ρ| \geq 0.95$ with the capacity fade trajectory on average across all datasets with monotone degradation profiles, including zero-shot test batteries, providing evidence that the representations encode degradation dynamics transferable to downstream tasks beyond battery response modelling. Code is available at https://github.com/BeArnab96/NOCE-Net.

cs.CE↗
arXiv2026

Learning to Reason with Selective Internal Feedback

Reinforcement learning from internal feedback can improve language models without ground-truth answers or external verifiers. However, confidence and correctness can diverge during training, and continued optimization of average self-certainty can increase confidence while degrading reasoning accuracy. We introduce SIF, a reinforcement learning method that combines comparative reward construction with selective policy updates. SIF compares ranked token-level self-certainty profiles across multiple windows and peers, assigning positive rewards only when both levels of voting provide sufficient support. Sample and group level filtering determines which responses contribute to policy optimization. Experiments on three backbones across 12 mathematical and scientific reasoning benchmarks show that SIF's final checkpoints achieve higher average accuracy than the best-validation checkpoints of Intuitor and Vigor, with a gain of 4.71 percentage points over Intuitor on Qwen2.5-Math-1.5B. Further analyses show better retention of accuracy during continued optimization, while test-time training experiments demonstrate sustained improvements with as few as four rollouts per prompt.

cs.AI↗