50 articles mentioning auto
arXiv:2609.03355v1 Announce Type: cross Abstract: Logit-based knowledge distillation for autoregressive language models usually aligns teacher and student next-token distributions over the entire vocabulary. However, this global objective overlooks relative preferences among likely token alternative
arXiv:2609.03478v1 Announce Type: new Abstract: We report on our ongoing project to develop a computational pipeline, AutoGraphForge, for an automated graph-theoretic conjecturing-refuting-formalizing-proving system. Conjecture generation is counterexample-guided and runs in rounds: a Graffiti3 gene
arXiv:2609.03622v1 Announce Type: cross Abstract: Test-time adaptation (TTA) offers a promising direction for improving speech enhancement models under mismatched acoustic conditions, without requiring access to labeled target data. In this work, we propose a single-utterance TTA method that regular
arXiv:2609.03629v1 Announce Type: cross Abstract: Recent advances in text-to-video (T2V) diffusion models have demonstrated remarkable generative capabilities, yet their reliance on loosely curated training data raises pressing safety and copyright concerns. Concept erasure offers a principled remed
arXiv:2604.01658v3 Announce Type: replace Abstract: Large language model (LLM)-based evolution is a promising approach for open-ended discovery, where progress requires sustained search and knowledge accumulation. Existing methods still rely heavily on fixed heuristics and hard-coded exploration rul
arXiv:2606.14202v5 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have advanced Automatic Heuristic Design (AHD) by enabling heuristic generation through reasoning and code synthesis. In LLM-based AHD, the LLM reasons about algorithm design and generates executable heuristic cod
arXiv:2609.03432v1 Announce Type: new Abstract: Automated evaluation of creativity tasks remains challenging for LLM-as-a-Judge, as LLM is susceptible to biases such as verbosity bias and leniency bias. Such limitations are particularly evident in Contextually-Grounded and Procedurally-Structured Ta
arXiv:2609.04147v1 Announce Type: cross Abstract: This paper presents a low-cost, open experimental platform for research in end-to-end autonomous driving with miniature Ackermann vehicles. The platform combines a physical vehicle, a printed urban track, data collection tools, trajectory registratio
arXiv:2601.10029v3 Announce Type: replace Abstract: Academic paper search is a fundamental task in scientific research, yet most existing approaches organize retrieval around predefined workflows or structured interaction protocols that struggle with complex, conditional queries. To address this lim
arXiv:2607.03166v2 Announce Type: replace-cross Abstract: Template-based contrastive synthesis is scalable, but its candidates often differ only in a few entity-slots while sequence-level optimization spreads supervision over mostly shared templates. We formalize this as the Resolution Mismatch Prob
arXiv:2608.27141v4 Announce Type: replace-cross Abstract: Large language model agents are increasingly deployed as autonomous loops. Starting from one human goal, such a system repeatedly discovers work, plans, executes tool calls, verifies outcomes and persists state across many unattended iteratio
arXiv:2609.03495v1 Announce Type: new Abstract: This paper examines the relationship between the parameters of autoencoder models and the statistical properties of the data on which they are trained. Autoencoders are defined as models with an encoder-decoder architecture, trained to reconstruct inpu
arXiv:2609.03753v1 Announce Type: new Abstract: As large language models (LLMs) become increasingly capable, the long-term value of AI systems depends not only on solving individual requests, but also on transforming experience and accumulated knowledge into durable, reusable competence. We introduc
arXiv:2609.02942v1 Announce Type: cross Abstract: LLM-as-a-Judge pipelines are increasingly used to evaluate AI-generated text, based on the assumption that judgments arise from reasoning over candidate responses with respect to a rubric. We show that this assumption warrants further scrutiny. Class
arXiv:2505.00284v3 Announce Type: replace-cross Abstract: Rapid advances in vision-language models (VLMs) have generated growing interest in their application to autonomous driving. A prevailing assumption is that successive VLM generations will continually improve driving performance and eventually
arXiv:2607.05915v3 Announce Type: replace Abstract: PCB routing is the task of connecting the nets of a board with copper traces under strict design rules, yet learning-based methods still lag behind rule-based routers. We introduce PCBWorld, an open-source engine-grounded PCB routing environment bu
arXiv:2609.03940v1 Announce Type: cross Abstract: Most previous work on speech enhancement (SE) based on masked generative modeling relied on discrete token representations of audio signals, obtained using neural audio codecs (NACs). However, a recent study has shown that continuous latent represent
arXiv:2511.10866v2 Announce Type: replace-cross Abstract: This paper proposes a Short-Window Sliding Learning framework for real-time violence detection in CCTV footages. Unlike conventional long-video training approaches, the proposed method divides videos into 1-2 second clips and applies Large La
arXiv:2512.09108v2 Announce Type: replace-cross Abstract: Agentic AI systems built on large language models (LLMs) offer significant potential for automating complex workflows, from software development to customer support. However, LLM agents often underperform due to suboptimal configurations; poo
arXiv:2606.07451v2 Announce Type: replace-cross Abstract: Vision-language models such as CLIP are highly useful for diverse tasks due to their shared image-text embedding space. Despite this, the image and text embeddings are often poorly aligned, affecting downstream performance. Recent work has hy
arXiv:2609.04170v1 Announce Type: new Abstract: Multi-agent AI science ecosystems rely on agents possessing tools that allow them to communicate, coordinate, and build on each other's work. Yet this shared infrastructure can also introduce vulnerabilities by creating a substrate for the contagious s
arXiv:2602.13473v3 Announce Type: replace Abstract: Although foundation models have achieved remarkable success in general domains, applying them to electroencephalography (EEG) analysis is constrained by substantial data requirements and large parameter counts, which incur prohibitive computational
arXiv:2508.15038v2 Announce Type: replace-cross Abstract: Wildlife field operations demand efficient parallel deployment methods to identify and interact with specific individuals, enabling simultaneous collective behavioral analysis, and health and safety interventions. Previous robotics solutions
arXiv:2609.03677v1 Announce Type: cross Abstract: Understanding the composition of large-scale autonomous driving datasets is essential for safety, robustness, and reliable operation across domains. For example, domain shift between locations could lead to the operating environment being misaligned
arXiv:2609.03931v1 Announce Type: cross Abstract: Generating complete 3D scenes from sparse, unconstrained views is a fundamental challenge in 3D vision which requires reasoning beyond observed content while remaining computationally tractable. Existing feed-forward reconstruction methods are inhere
arXiv:2609.03553v1 Announce Type: new Abstract: Policy analysis requires more than predicting whether a proposal will pass: it requires identifying who will be affected, how those actors respond, and what follows. LLM-based policy simulations model these processes at scale, but their validity is har
arXiv:2604.09038v2 Announce Type: replace-cross Abstract: Robust geo-localization under changing environmental and operational conditions is critical for long-term aerial autonomy. Aerial visual place recognition (VPR) commonly uses pre-acquired remote-sensing imagery of the intended operating area,
arXiv:2505.22451v2 Announce Type: replace Abstract: Large Reasoning Models (LRMs) have made significant progress in mathematical capabilities in recent times. However, these successes have been primarily confined to competition-level problems. In this work, we propose AI Mathematician (AIM) framewor
arXiv:2603.19828v4 Announce Type: replace Abstract: Autoformalization aims to produce formal statements that compile and faithfully preserve the intended meaning of informal mathematics. Yet standard single-output evaluation collapses this many-to-many structure into a single prediction. For downstr
arXiv:2609.02624v1 Announce Type: cross Abstract: Assessing vulnerability detection tools for smart contracts requires datasets with known ground truth, yet such datasets are scarce and difficult to build by hand. We propose an approach that uses Large Language Models (LLMs) to automatically inject
arXiv:2608.28945v3 Announce Type: replace Abstract: Automating alignment research may accelerate progress toward aligned AI, but whether it does is hard to measure. Luckily, many alignment failures, such as deception, sycophancy, and jailbreaks, are already measurable by public benchmarks. We study
arXiv:2306.06865v2 Announce Type: replace-cross Abstract: Clinical guidelines underscore the importance of regularly monitoring and surveilling arteriovenous fistula (AVF) access in hemodialysis patients to promptly detect any dysfunction. Although phono-angiography/sound analysis overcomes the limi
arXiv:2604.08552v3 Announce Type: replace-cross Abstract: Descriptive scientific metadata in public repositories are often incomplete and inconsistent with community standards and ontologies, limiting data FAIRness. Large language models (LLMs) offer a promising approach to automatically standardizi
arXiv:2609.01659v1 Announce Type: cross Abstract: Chain-of-thought (CoT) reasoning powers generative models by eliciting intermediate steps before producing an answer. In autonomous driving, the answer is a continuous action. Thus its reasoning must share the same spatiotemporal structure as the phy
arXiv:2607.17117v2 Announce Type: replace-cross Abstract: Sparse autoencoders (SAEs) decompose language model activations into sparse features, yet these models traditionally encode each token independently, failing to expose information that persists across a sequence. We first show that temporal p
arXiv:2609.01623v1 Announce Type: cross Abstract: Autonomous and intelligent transportation systems operate in complex urban environments where safety depends on interactions among vehicle behavior, environmental conditions, and vulnerable road users (VRUs) such as pedestrians and cyclists. Most adv
arXiv:2609.02861v1 Announce Type: cross Abstract: Autonomous robots powered by deep learning face a fundamental auditability challenge: when incidents occur, investigators cannot reconstruct why the system made specific decisions. This paper presents TRACE (Transparent Reasoning Architecture for Cre
arXiv:2609.01567v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) provide useful priors for interactive decision-making, but using them directly as policies is expensive and brittle: they must be queried at every step, do not improve from environment interaction, and can repeat syste
arXiv:2609.01971v1 Announce Type: new Abstract: AI is rapidly advancing neuroscience, yet many laboratories fail to fully unleash its potential due to significant interdisciplinary barriers. While pre-trained neural models for physiological data are progressing quickly, their heterogeneous architect
arXiv:2609.01609v1 Announce Type: new Abstract: While diffusion models effectively capture multimodal behavioral priors for autonomous driving, offline reinforcement learning (RL) policies remain susceptible to distribution shift, heavy-tailed risk signals, out-of-distribution (OOD) action generatio
arXiv:2609.01987v1 Announce Type: cross Abstract: Patient exams in the cancer diagnosis and staging process typically generate several whole slide images (WSIs). One of the initial steps in training models on WSI data is identifying one or a few slides containing tumor or other diagnostic biomarkers
arXiv:2608.29270v2 Announce Type: replace-cross Abstract: Autoformalization translates informal mathematical theorems into code for proof assistants such as Lean. A central challenge is that current evaluation metrics can accept type-correct but misaligned statements or reject correct statements wri
arXiv:2609.02110v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) commonly evaluate the spatial derivatives appearing in partial differential equation residuals using automatic differentiation (AD), whose computational and memory costs can become substantial when multiple or h
arXiv:2606.29894v2 Announce Type: replace-cross Abstract: As agentic AI systems tackle more complex mathematical tasks, they increasingly rely on information retrieval (IR) to search problem databases, theorem libraries, and educational resources. However, choosing the right retriever remains diffic
arXiv:2609.01775v1 Announce Type: cross Abstract: Automated repair of Hardware Description Language (HDL) designs remains challenging due to the large search space of candidate repairs and the strict syntactic and semantic constraints imposed by HDL grammars. Generic mutation strategies overwhelming
arXiv:2609.02250v1 Announce Type: cross Abstract: Ride-sharing, which allows multiple passengers with different origin-destination (OD) pairs to share a single vehicle, is a challenging operational problem, as it requires orders with different OD pairs to be efficiently bundled and assigned to vehic
arXiv:2609.02231v1 Announce Type: new Abstract: Interview assessment requires per-criterion judgments grounded in behavioral evidence, yet surging applicant volumes have made human-only evaluation costly and inconsistent, while existing AI approaches yield opaque scores without traceable rationale.
arXiv:2609.01675v1 Announce Type: cross Abstract: Accurate large-scale wildfire spread modelling requires models that capture both the environmental conditions associated with fire occurrence and the local dynamics of fire propagation. We propose a three-stage framework that combines a Random Forest
arXiv:2607.23286v2 Announce Type: replace Abstract: Automatic feature engineering (AutoFE) for tabular data requires discovering informative transformations from a large program space. Existing approaches suffer from three limitations: classical methods rely on fixed operator libraries with limited
arXiv:2609.01622v1 Announce Type: cross Abstract: The rise of agentic AI has catalyzed a shift toward self-iterating systems, opening new frontiers for the autonomous optimization of production recommender models. This paper presents the empirical validation of a knowledge-driven autonomous agent sy