Recovering Wasted Compute in Autoresearch Agents
arXiv:2608.10424v1 Announce Type: new Abstract: A slew of recent works develop agents for solving research problems end-to-end, a paradigm increasingly referred to as autoresearch. Such agents have in
Knowledge catalogue
arXiv:2608.10424v1 Announce Type: new Abstract: A slew of recent works develop agents for solving research problems end-to-end, a paradigm increasingly referred to as autoresearch. Such agents have in
arXiv:2608.10669v1 Announce Type: new Abstract: Large language model (LLM) agents combine language-based reasoning with external tools to perform complex tasks. Adversarial inputs can exploit interact
arXiv:2608.10812v1 Announce Type: cross Abstract: We study reference-free post-training for multilingual machine translation with open large language models. Starting from the supervised-finetuned MiL
arXiv:2412.09486v2 Announce Type: replace-cross Abstract: The literature reflects a mutually beneficial relationship between machine learning and quantum computing, where progress in one field frequen
arXiv:2608.10549v1 Announce Type: new Abstract: Achieving high accuracy in laser-based cutting of optical films requires careful tuning of parameters such as focal length and laser power beam, adjuste
arXiv:2604.02621v2 Announce Type: replace Abstract: Reinforcement Learning (RL) substantially improves the reasoning capabilities of language models, but most existing RL fine-tuning approaches rely e
arXiv:2608.10970v1 Announce Type: cross Abstract: Recent advances in Large Language Models (LLMs) have demonstrated strong capabilities in generating semantically relevant concepts and relations, maki
arXiv:2608.10905v1 Announce Type: new Abstract: On-policy distillation (OPD) applies token-level teacher supervision to student-generated trajectories, but this supervision is not always reliable. Exi
arXiv:2608.11045v1 Announce Type: cross Abstract: ReRound (Reconstructive Rounding) is a post-training quantization method that addresses the midpoint ambiguity inherent in standard round-to-nearest (
arXiv:2608.09971v1 Announce Type: cross Abstract: Over the past few years, the rapid development of machine learning (ML) models for weather forecasting has produced deterministic models whose medium-
arXiv:2608.10590v1 Announce Type: new Abstract: Vision Transformers (ViTs) are widely believed to require more labeled data than CNNs for industrial dense prediction. Through controlled experiments on
arXiv:2608.10725v1 Announce Type: new Abstract: Large language models (LLMs) often rely on shortcuts rather than systematic reasoning, raising safety concerns in medical applications. Allowing models
arXiv:2608.10524v1 Announce Type: cross Abstract: Driven by the rapid advancement of vision-language representation learning, Text-based Image Retrieval (TBIR) has made notable progress. However, exis
arXiv:2608.10657v1 Announce Type: cross Abstract: Leukemia cell image classification is challenged by real-world domain shifts from acquisition, staining, illumination, and site protocols, causing sin
arXiv:2608.10553v1 Announce Type: cross Abstract: Conformal prediction (CP) provides distribution-free prediction intervals for fixed forecasters, but its standard calibration procedure is often ineff
arXiv:2608.10416v1 Announce Type: cross Abstract: We present a theoretical foundation for inverse-distance attention, from its Euclidean prototype (Resolver) to its non-Euclidean realization (Riemann
arXiv:2602.20403v2 Announce Type: replace Abstract: We study distributionally robust online learning, where a risk-averse learner updates decisions sequentially to guard against worst-case distributio
arXiv:2608.11175v1 Announce Type: new Abstract: For autonomous space exploration, robotic agents need to perform motion planning in which environmental interactions may be unknown. Learning these inte
arXiv:2608.10471v1 Announce Type: new Abstract: Prompt optimizers automate the search for prompts that improve language-model performance, but existing methods rely on a predefined optimization proced
arXiv:2502.02068v3 Announce Type: replace-cross Abstract: This paper introduces RoSeMary, the first-of-its-kind ML/Crypto codesign watermarking framework that regulates LLM-generated code to avoid int
arXiv:2608.10529v1 Announce Type: cross Abstract: The multi-armed bandit problem is a central framework in sequential decision-making, extensively studied under sub-Gaussian reward assumptions. Howeve
arXiv:2608.10872v1 Announce Type: cross Abstract: We present a robust safety-filtering framework for input-constrained underactuated linear systems subject to unknown disturbances. A baseline H-infty
arXiv:2608.10656v1 Announce Type: new Abstract: Contact-based industrial inspection requires aerial platforms to maintain stable interaction while rejecting disturbances. Underactuated aerial manipula
arXiv:2608.09999v1 Announce Type: cross Abstract: In transfer learning, the choice of source model largely influences the performance on a target dataset. Still, selecting a fitting source remains a c
arXiv:2608.11080v1 Announce Type: new Abstract: Rail transit systems play a vital role in urban mobility and economic development. As key components of such systems, rail transit stations function as
arXiv:2608.10766v1 Announce Type: new Abstract: Explainable Artificial Intelligence (XAI) seeks to explain how an Artificial Intelligence (AI) system arrived at a particular decision. We propose ''Rul
arXiv:2608.10933v1 Announce Type: new Abstract: Text-to-Video (T2V) generative models are vulnerable to jailbreak attacks in real-world deployment, leading them to produce harmful or inappropriate con
arXiv:2608.10513v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) remain vulnerable to jailbreak attacks that exploit visual inputs to bypass safety alignment inherited from their
arXiv:2608.10497v1 Announce Type: new Abstract: While foundation models have significantly advanced human recognition across diverse modalities, they predominantly rely on static, geometric feature ex
arXiv:2608.11142v1 Announce Type: new Abstract: Agricultural monitoring faces unique challenges, arising from the landscape's complex temporal, phenological, and climate dynamics, yet monitoring them
arXiv:2608.10157v1 Announce Type: new Abstract: Self-improving agents seek to reduce the human engineering effort behind AI systems by enabling them to evolve and self-improve their performance over t
arXiv:2601.07218v2 Announce Type: replace Abstract: We present SceneNAT, a masked non-autoregressive Transformer for 3D indoor scene synthesis from natural language instructions. It generates complete
arXiv:2608.11152v1 Announce Type: cross Abstract: Modern reinforcement learning (RL) post-training pipelines for large language models (LLMs) increasingly combine rollout workloads across multiple dom
arXiv:2608.11034v1 Announce Type: cross Abstract: In LLM pre-training, synchronization propagates rank-local stalls, slowdowns, and numerical errors into job-wide symptoms, obscuring their origin. Exi
arXiv:2608.10670v1 Announce Type: new Abstract: At corpus sizes typical of low-resource dialects, single-run comparisons can yield gains that do not replicate. We show this for Garhwali, an under-reso
arXiv:2608.10997v1 Announce Type: new Abstract: Advancing autonomy for surface vessels requires systematic evaluation of their sensing and perception subsystems. Yet, maritime environments impose uniq
arXiv:2608.10289v1 Announce Type: new Abstract: Deep neural networks are increasingly deployed in safety-critical domains as perception modules, where failures are often caused due to rare and under-r
arXiv:2608.10144v1 Announce Type: new Abstract: We consider federated parameter efficient fine-tuning of large neural networks with low-rank adaptation (LoRA,~Hu et al. 2022). Combining LoRA with fede
arXiv:2508.07617v2 Announce Type: replace-cross Abstract: AI has the potential to augment human decision making. However, even high-performing models can produce inaccurate predictions when deployed.
arXiv:2608.10676v1 Announce Type: new Abstract: Large language model (LLM)-based search agents answer questions through multi-step interactions with external environments. However, providing complete
arXiv:2608.10224v1 Announce Type: new Abstract: Enterprise support agents operate in rapidly changing environments where policies, product capabilities, and knowledge bases evolve continuously, making
arXiv:2608.10708v1 Announce Type: new Abstract: Recent Vision Foundation Models (VFMs) predict depth, camera pose, and pointmap in a single forward pass without per-scene optimization, achieving stron
arXiv:2608.11030v1 Announce Type: cross Abstract: Patent retrieval and matching based on large language models (LLMs) play a vital role in intellectual property protection. However, due to the complex
arXiv:2608.10896v1 Announce Type: cross Abstract: Constant-stepsize temporal-difference (TD) learning is attractive for policy evaluation, but inference from a single Markov trajectory must account fo
arXiv:2608.10888v1 Announce Type: new Abstract: Per-point uncertainty models are important in structured-light 3D reconstruction for probabilistic registration, fusion, and quality assessment. In prac
arXiv:2607.15606v2 Announce Type: replace Abstract: Synthetic sequential tabular data are increasingly used for privacy-preserving data sharing and data-driven research, but evaluating their fidelity
arXiv:2608.10240v1 Announce Type: cross Abstract: Multi-modal sequential recommenders assume every item carries every modality, but real product catalogs often miss images or text, and a model trained
arXiv:2608.10392v1 Announce Type: cross Abstract: Mixture-of-experts (MoE) models have recently moved beyond routing a fixed number of complete experts. Shared-expert designs preserve reusable knowled
arXiv:2608.10016v1 Announce Type: cross Abstract: Heterogeneous federated systems require agents to learn and exchange informative representations despite differences in data distributions, sensing mo
arXiv:2604.03337v2 Announce Type: replace Abstract: Genotype-environment (GxE) interactions can influence the performance of genotypes across diverse environments, limiting the reliability of genotype
arXiv:2608.10091v1 Announce Type: new Abstract: We present a method for training imperceptible visual watermarks to coexist with other such watermarks. Recent work has shown that independently trained
arXiv:2608.10216v1 Announce Type: cross Abstract: Agent frameworks ship quality gates that compare text blocks by embedding-cosine similarity and decide at a fixed cutoff. Deduplication filters, seman
arXiv:2608.10615v1 Announce Type: new Abstract: Discrete diffusion models for categorical generation are defined by a corruption kernel, which determines the intermediate state space and the associate
arXiv:2607.16943v2 Announce Type: replace Abstract: Safety validation at signalized intersections remains a critical bottleneck for the deployment of autonomous driving systems (ADS), as these scenari
arXiv:2602.13319v2 Announce Type: replace Abstract: Perspective-aware AI requires modeling evolving internal states---goals, emotions, contexts---not merely preferences. Progress is limited by a data
arXiv:2608.10538v1 Announce Type: new Abstract: Agent skills represent a standardized format for packaging procedural knowledge and domain expertise, serving within agent harness systems as an essenti
arXiv:2608.10775v1 Announce Type: new Abstract: Computer-using agents can perceive rich software interfaces, yet their decisions often lack visual procedural memory: they may recognize individual cont
arXiv:2608.11079v1 Announce Type: new Abstract: Self-evolving agents accumulate reusable skills by appending successful procedures and failure fixes. Over time, the same requirement is often restated
arXiv:2608.11136v1 Announce Type: new Abstract: Logic Tensor Networks (LTN) provide a neurosymbolic framework in which first-order logic is interpreted through tensor operations, enabling logical cons
arXiv:2608.10730v1 Announce Type: cross Abstract: The pursuit of artificial general intelligence (AGI) rests on a seemingly self-evident premise: that general intelligence, the kind of flexible, domai