49 articles mentioning Ling-2.6-flash
arXiv:2607.15467v1 Announce Type: new Abstract: Knowledge distillation enables an adversary to replicate a proprietary classifier by querying its prediction interface and training a surrogate on the returned probability vectors. Antidistillation sampling, proposed for large language models, counters
arXiv:2607.15870v1 Announce Type: new Abstract: Human label variation in natural language inference is increasingly treated as signal rather than noise, but how much of it formal semantic structure explains has not been measured directly. We measure it on the 3,113 SNLI and MNLI items of ChaosNLI, u
arXiv:2607.08362v2 Announce Type: replace Abstract: Vietnam's ethnic minority languages are almost absent from the field of Natural Language Processing (NLP), and the challenge goes beyond data scarcity: Cham, Khmer, and Tay-Nung differ sharply in script, Vietnamese contact, and standardization, con
arXiv:2606.25971v2 Announce Type: replace Abstract: Modern neural network training relies on optimizers such as Adam and Muon which act on each weight matrix as a single object. Yet every weight matrix carries two distinct quantities -- a \emph{magnitude} and a \emph{direction} -- and all optimizers
arXiv:2607.15511v1 Announce Type: cross Abstract: Serverless computing provides automatic resource management and pay-per-use execution, but effective autoscaling remains challenging because of dynamic workloads, cold-start latency, and dependencies among functions. We present a dependency-aware aut
arXiv:2606.17522v2 Announce Type: replace Abstract: Deep neural networks are widely believed to derive their expressive power from their ability to form \textbf{hierarchical representations}, capturing progressively more abstract and compositional features across layers. In language modeling, \textb
arXiv:2606.16073v2 Announce Type: replace Abstract: Sampling from complex, unnormalized probability densities is a fundamental challenge in Bayesian inference and probabilistic modeling. While Markov chain Monte Carlo (MCMC) methods provide asymptotic guarantees, they often suffer from slow mixing a
arXiv:2607.11889v2 Announce Type: replace-cross Abstract: Large language models trained on unrestricted internet corpora inevitably embed information from the future, introducing lookahead bias that compromises the validity of backtests and causal inference in finance and the social sciences. Point-
arXiv:2607.15577v1 Announce Type: cross Abstract: Causal bandits exploit structural relationships among variables to share information across interventions and accelerate the identification of high-reward decisions. In many applications, however, some variables cannot be directly manipulated, even t
arXiv:2607.15740v1 Announce Type: cross Abstract: As Text-to-Image (T2I) systems rapidly advance, evaluating the cultural authenticity of synthesized content has become increasingly important for fair and trustworthy generative AI. Existing T2I evaluation metrics and multimodal judges often rely on
arXiv:2607.15774v1 Announce Type: cross Abstract: Explainable AI (XAI) for time series has seen significant algorithmic growth, but its utility in providing measurable performance gains for downstream tasks remains under-explored. This paper bridges this gap by introducing drXAI, a novel methodology
arXiv:2607.15861v1 Announce Type: cross Abstract: Moderation systems increasingly rely on external toxicity tools, but those tools are unreliable under code-mixing, transliteration, slang, and language mismatch. We study the \emph{conditional reliability} of toxicity priors in Indian multilingual an
arXiv:2607.11436v2 Announce Type: replace Abstract: Vision-language models increasingly succeed on multimodal reasoning benchmarks, yet their visual evidence often becomes unstable once it enters the language stack, weakening evidence-grounded reasoning. To understand this fragility, we examine the
arXiv:2607.15509v1 Announce Type: cross Abstract: We present a fully automated closed-loop AutoML framework that uses GPT-5, GPT-4o, and Claude Sonnet 4 as autonomous neural architecture designers for cross-lingual handwritten optical character recognition. Each large language model independently ge
arXiv:2607.15620v1 Announce Type: cross Abstract: Self-driving laboratories increasingly rely on low-cost liquid handlers such as the Opentrons OT-2, which ship without the pressure-based aspiration monitoring of Hamilton or Tecan systems and are typically run open-loop. Two failure modes go undetec
arXiv:2510.22204v3 Announce Type: replace-cross Abstract: Reliable assessment of safe landing sites in unstructured environments is essential for deploying Unmanned Aerial Vehicles (UAVs) in real-world applications such as delivery, inspection, and surveillance. Existing learning-based approaches of
arXiv:2604.04593v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) grounds large language models in external medical knowledge, yet standard retrievers frequently surface hard negatives that are semantically close to the query but describe clinically distinct conditions.
arXiv:2606.22776v2 Announce Type: replace-cross Abstract: Non-autoregressive neural solvers amortize computation across traveling salesman problem (TSP) instances, but models trained on random Euclidean instances can degrade when the number or spatial distribution of nodes changes. We study whether
arXiv:2606.29538v4 Announce Type: replace-cross Abstract: Skills are a useful abstraction for software agents, turning human and agent experience into reusable procedural knowledge. Yet existing skill libraries are mostly hand-written, text-centric, or derived from agent traces, leaving tutorial vid
arXiv:2607.14186v2 Announce Type: replace-cross Abstract: Synthesizing training data to scale agent capabilities in LLM post-training is bottlenecked by substrate-bound task synthesis: tasks are generated from fixed tools, repositories, or skill graphs, so expanding coverage requires manual substrat
arXiv:2607.16085v1 Announce Type: new Abstract: Increasingly, speech and language processing tasks take either audio or text directly rather than extracting features from these as the input to the classifier or regressor. Often these systems make use of complex, for example transformer-based, proces
arXiv:2607.16117v1 Announce Type: new Abstract: Language models encode text as subword tokens, raw bytes, or rendered pixels, but these encodings are usually compared under modeling constraints that expose different amounts of linguistic content to models across different languages. We instead ask w
arXiv:2607.15313v1 Announce Type: new Abstract: The scaling hypothesis assumes that increasing model parameters yields emergent reasoning capabilities. This position paper argues that applying this probabilistic paradigm to generic quantum circuit synthesis is a directional error. Unlike natural lan
arXiv:2607.15682v1 Announce Type: new Abstract: Sampling from an unnormalized Boltzmann density requires proposals that move probability mass globally while retaining enough path-probability information for statistical correction. We introduce Neural Non-Equilibrium Hamiltonian Monte Carlo (NHMC), a
arXiv:2607.11734v2 Announce Type: replace-cross Abstract: Differentiable simulators have advanced policy learning and model-based control across robotic tasks. Yet actuator dynamics remain underexplored and can be a major source of sim-to-real error, particularly on low-cost platforms, where the lin
arXiv:2606.18824v2 Announce Type: replace-cross Abstract: Pedestrian trajectory prediction from an on-board ego-centric camera is challenging since it depends on complex interactions with vehicles and scene context, as well as the intention of the pedestrian. The task becomes even more challenging s
arXiv:2511.20687v4 Announce Type: replace-cross Abstract: This paper presents a novel hybrid approach for coupling subdomain-local non-intrusive Operator Inference (OpInf) reduced order models (ROMs) with each other and with subdomain-local high-fidelity full order models (FOMs) with using the overl
arXiv:2607.15907v1 Announce Type: new Abstract: The stochastic fundamental diagram (SFD) provides a probabilistic description of the relationship between traffic density and flow or speed, enabling uncertainty-aware traffic modeling. However, existing stochastic models frequently struggle to accommo
arXiv:2607.14349v1 Announce Type: cross Abstract: While Large Language Models (LLMs) excel in many general NLP tasks, their formal reasoning capabilities are often compromised by content effects, demonstrating a measurable bias towards real-world plausibility. In this paper, we present our system fo
arXiv:2607.14110v1 Announce Type: cross Abstract: Human dialogue involves more than exchanging information; it also expresses beliefs, emotions, and subjective cognitive styles. Yet current AI dialogue systems often enforce semantic uniformity, sacrificing diversity and interpretability. We present
arXiv:2607.14112v1 Announce Type: cross Abstract: Large language models (LLMs) are evaluated as though perfect reliability is achievable for any task given sufficient scale. We show this assumption is information-theoretically unjustified. Every generative task has a reliability ceiling that no mode
arXiv:2607.14921v1 Announce Type: cross Abstract: Machine learning models are increasingly adapted in various domains. However, adversarial examples pose a significant threat to the reliable deployment of these models. In recent years, some powerful adversarial example attacks have been proposed for
arXiv:2607.14659v1 Announce Type: cross Abstract: Interoperability between heterogeneous modeling tools remains a significant challenge in Model-Driven Engineering (MDE), particularly in the automotive domain where multiple modeling languages, as well as defacto standard proprietary and open-source
arXiv:2607.15229v1 Announce Type: new Abstract: We develop data-driven algorithms for maintaining $N$ independent identical machines under a \textit{block replacement policy}, in which each machine is replaced upon failure and all machines are jointly replaced at regular intervals of length $k$. The
arXiv:2607.14396v1 Announce Type: new Abstract: Product catalogs are the backbone of e-commerce sites, yet a large number of structured attributes (SAs) -- such as material, color, and shape -- often have missing values. Typically, SA values are extracted from product information, including titles a
arXiv:2607.14186v1 Announce Type: cross Abstract: Scaling executable agent training data is bottlenecked by substrate-first methods that tie task generation to predefined tools, repositories, or skill graphs: expanding coverage requires manual expansion of the substrate, each new domain demands a be
arXiv:2606.29059v2 Announce Type: replace-cross Abstract: World modeling requires forecasting uncertain futures while preserving information useful for downstream perception. Existing visual world models often struggle to satisfy both goals: VAE-based stochastic models operate in low-dimensional rec
arXiv:2604.23743v2 Announce Type: replace-cross Abstract: Variational quantum circuits train poorly on chaotic forecasting, usually blamed on barren plateaus (exponentially vanishing gradients). Using an exactly simulable four-qubit variational quantum physics-informed circuit fit to Lorenz-63, we s
arXiv:2607.14386v1 Announce Type: new Abstract: Data science tasks span from closed-ended information extraction to open-ended analysis, presenting significant challenges for automation. Recent AI agents powered by language models show promise for handling such complex tasks. However, existing agent
arXiv:2607.14816v1 Announce Type: cross Abstract: Large Language Models (LLMs) perform differently on identical programming tasks when prompted in different natural languages, a phenomenon known as language bias. While this behavior has been widely studied for general text generation, its impact on
arXiv:2607.15275v1 Announce Type: cross Abstract: Recent robot foundation models operate with single-step or short-history visuomotor context. We introduce Test-Time-Training Robot Policies (RoboTTT), a robot model and training recipe that scale visuomotor context to 8K timesteps, three orders of ma
arXiv:2607.12121v2 Announce Type: replace-cross Abstract: Diffusion models have become the central backbone for modern image, video, and audio generation, but their efficient service remains a challenge. Unlike autoregressive decoding, diffusion inference repeatedly updates high-dimensional spatial
arXiv:2607.14106v1 Announce Type: cross Abstract: In this paper we introduce token time continuous diffusion (TTCD), a new diffusion language model which (a) operates in continuous space, deterministically mapping Gaussian noise to a final token canvas with no further sampling, and crucially (b) inc
arXiv:2607.14285v1 Announce Type: cross Abstract: Safety alignment in LLMs aims to align models with human values, but which values take precedence when they conflict? We investigate this question in the context of tool-calling LLM agents deployed in regulated industries, where agents processing con
arXiv:2509.19869v2 Announce Type: replace-cross Abstract: Data-driven control increasingly relies on deep models for complex systems whose first-principles models are difficult to obtain. For reliable deployment, however, learned dynamics should respect physical structure and lead to tractable optim
arXiv:2607.15163v1 Announce Type: cross Abstract: Humanoid control requires natural whole-body coordination, precise real-time responses to control signals, and robust generalization across diverse environmental contexts, making it a cornerstone for generalist embodied agents. Behavior Foundation Mo
arXiv:2607.15065v1 Announce Type: cross Abstract: Predictive world models enable robots to plan by imagining the outcomes of their actions, but their value for control hinges on generating many rollouts quickly. This creates a bottleneck for diffusion-based world models: multistep sampling makes eac
arXiv:2607.15067v1 Announce Type: new Abstract: This article presents a novel estimator for performing off-policy evaluation using only offline data for contextual bandits. The proposed estimator, Kernel-WIS is demonstrated to be asymptotically consistent and to empirically outperform strong baselin
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 ser