Learning the Preferences of a Learning Agent
arXiv:2605.09217v1 Announce Type: new Abstract: For AI systems to be useful to humans, they must understand and act in accordance with our values and preferences. Since specifying preferences is a har
Knowledge catalogue
arXiv:2605.09217v1 Announce Type: new Abstract: For AI systems to be useful to humans, they must understand and act in accordance with our values and preferences. Since specifying preferences is a har
arXiv:2605.08811v1 Announce Type: cross Abstract: This paper investigates the learning theory of Transformer networks for regression tasks on the compact Euclidean domain [0,1]^d and d-dimensional com
arXiv:2605.09859v1 Announce Type: new Abstract: Fine-grained image retrieval (FGIR) typically relies on supervision from seen categories to learn discriminative embeddings for retrieving unseen catego
arXiv:2605.09448v1 Announce Type: new Abstract: The transition to First-Price Auctions (FPA) in digital advertising has spurred significant research, yet existing work typically assumes access to a va
arXiv:2605.09818v1 Announce Type: new Abstract: Reinforcement learning (RL) in healthcare has had mixed results, with reward sparsity, unreliable off-policy evaluation, and deployment-simulation gap a
arXiv:2605.08978v1 Announce Type: new Abstract: Recent advancements in agentic test-time scaling allow models to gather environmental feedback before committing to final actions. A key limitation of e
arXiv:2508.14137v2 Announce Type: replace Abstract: The Macroscopic Fundamental Diagram is a popular tool used to describe traffic dynamics in an aggregated way, with applications ranging from traffic
arXiv:2605.09963v1 Announce Type: new Abstract: Existing self-supervised learning (SSL) methods primarily learn object-invariant representations but often neglect the spatial structure and relationshi
arXiv:2605.10151v1 Announce Type: new Abstract: This paper addresses the problem of learning to sparsify stochastic linear bandits, where a decision-maker sequentially selects actions from a high-dime
arXiv:2602.17546v2 Announce Type: replace Abstract: Instruction-following language models are trained to be helpful and safe, yet their safety behavior can deteriorate under benign fine-tuning and wor
arXiv:2605.09685v1 Announce Type: cross Abstract: The core challenge in unsupervised anomaly detection is identifying abnormal patterns without prior knowledge of their characteristics. While existing
arXiv:2602.00877v2 Announce Type: replace Abstract: Low speed does not always guarantee safety in off-road driving. For instance, crossing a ditch may be risky at a low speed due to the risk of gettin
arXiv:2605.09183v1 Announce Type: new Abstract: Behavior cloning provides strong imitation learning guarantees when training and test environments share the same dynamics. However, in many deployment
arXiv:2601.21410v3 Announce Type: replace-cross Abstract: Large language models (LLMs) encode rich semantic knowledge that can be useful for supervised learning, but their outputs are unreliable as st
arXiv:2605.06394v1 Announce Type: cross Abstract: These lecture notes introduce some topics of classical statistical physics, particularly those that are relevant for neural networks and deep learning
arXiv:2605.10186v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly integrated into legal drafting and research workflows, where incorrect citations or fabricated precedent
arXiv:2512.23025v2 Announce Type: replace-cross Abstract: Multimodal health sensing offers rich behavioral signals for assessing mental health, yet translating these numerical time-series measurements
arXiv:2510.08592v3 Announce Type: replace-cross Abstract: Test-Time Scaling (TTS) improves LLM reasoning by exploring multiple candidate responses and then operating over this set to find the best out
arXiv:2509.25742v4 Announce Type: replace Abstract: Graph Contrastive Learning (GCL) has shown strong promise for unsupervised graph representation learning, yet its effectiveness on heterophilic grap
arXiv:2508.16070v3 Announce Type: replace Abstract: Approximately 283 million people worldwide live with visual impairments, motivating increasing research into leveraging Visual Language Models (VLMs
arXiv:2605.09404v1 Announce Type: cross Abstract: Targeted data selection aims to identify training samples from a large candidate pool that improve performance on a specific downstream task. Many rec
arXiv:2505.02184v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used for generating parallel scientific codes, with a primary focus on generating functionally correct
arXiv:2605.09764v1 Announce Type: cross Abstract: LLM-guided evolutionary methods such as AlphaEvolve have proven effective in domains like math, systems research, and algorithmic discovery, but their
arXiv:2605.08805v1 Announce Type: new Abstract: Audio-Visual Segmentation (AVS) targets pixel level localization of sounding emitting objects in videos. However, existing models rely on dense cross-mo
arXiv:2605.10810v1 Announce Type: new Abstract: We introduce an automatically generated benchmark for predicting hidden text in technical papers. A paper supplies visible context X and a hidden contin
arXiv:2509.20786v3 Announce Type: replace Abstract: Training deep neural networks with noise and data heterogeneity is a major challenge. We introduce Lightweight Learnable Adaptive Weighting (LiLAW),
arXiv:2510.17671v2 Announce Type: replace-cross Abstract: Many real-world optimization problems are guided by complex, subjective preferences that are difficult to express as explicit closed-form obje
arXiv:2605.10319v1 Announce Type: new Abstract: Layered image assets are widely used in real-world creative workflows, enabling non-destructive iteration and flexible re-composition. Recent advances i
arXiv:2505.17204v3 Announce Type: replace-cross Abstract: The sliced Wasserstein flow (SWF), a nonparametric and implicit generative gradient flow, is transformed into a Liouville partial differential
arXiv:2605.09384v1 Announce Type: cross Abstract: The reasoning gap between large and compact vision-language models (VLMs) limits the deployment of medical AI on portable clinical devices. Compact VL
arXiv:2605.10779v1 Announce Type: cross Abstract: The rapid proliferation of LLM-based autonomous agents in real operating system environments introduces a new category of safety risk beyond content s
arXiv:2605.10593v1 Announce Type: new Abstract: We demonstrate LLARS (LLM Assisted Research System), an open-source platform that bridges the gap between domain experts and developers for building LLM
arXiv:2605.10641v1 Announce Type: cross Abstract: Large Vision-Language Models (VLMs) are successful in addressing a multitude of vision-language understanding tasks, such as Visual Question Answering
arXiv:2605.08985v1 Announce Type: new Abstract: Visual encoding constitutes a major computational bottleneck in Multimodal Large Language Models (MLLMs), especially for high-resolution image inputs. T
arXiv:2605.09015v1 Announce Type: new Abstract: Sardinian, a Romance language with roughly one million speakers, has minimal presence in modern NLP. Commercial services do not support it, and current
arXiv:2605.08326v1 Announce Type: cross Abstract: As Large Language Models (LLMs) transition into conversational agents, generative advertising emerges as a crucial monetization strategy. However, emb
arXiv:2605.09252v1 Announce Type: new Abstract: Tool-augmented LLM agents tend to call tools indiscriminately, even when the model can answer directly. Each unnecessary call wastes API fees and latenc
arXiv:2605.08898v1 Announce Type: cross Abstract: Large Language Models (LLMs) increasingly employ alignment techniques to prevent harmful outputs. Despite these safeguards, attackers can circumvent t
arXiv:2505.07027v2 Announce Type: replace Abstract: Retrosynthesis, the process of breaking down a target molecule into simpler precursors through a series of valid reactions, stands at the core of or
arXiv:2605.09518v1 Announce Type: new Abstract: Meta-learning for algorithm selection relies on a meta-dataset in which each row corresponds to a supervised learning dataset described by meta-features
arXiv:2503.14434v3 Announce Type: replace-cross Abstract: Automated feature engineering plays a critical role in improving predictive model performance for tabular learning tasks. Traditional automate
arXiv:2605.09542v1 Announce Type: new Abstract: Extracting multi-step explanations from knowledge graphs poses a combinatorial challenge requiring both heuristic guidance (as candidates proliferate wi
arXiv:2605.08448v1 Announce Type: new Abstract: Semi-supervised learning approaches have been investigated as a means to enhance the analysis of social media data in disaster management contexts. In t
arXiv:2605.10574v1 Announce Type: new Abstract: As artificial intelligence advances, models are not improving uniformly. Instead, progress unfolds in a jagged fashion, with capabilities growing uneven
arXiv:2605.08247v1 Announce Type: cross Abstract: GCC and LLVM underpin much of modern software infrastructure, relying on distinct Intermediate Representations (IRs) to drive optimizations and code g
arXiv:2605.08321v1 Announce Type: cross Abstract: LLMs are increasingly capable of persuasion, which raises the question of how to protect users against manipulation. In a preregistered user study (N=
arXiv:2605.10401v1 Announce Type: new Abstract: Efficient branching policies are essential for accelerating Mixed Integer Linear Programming (MILP) solvers. Their design has long relied on hand-crafte
arXiv:2605.10807v1 Announce Type: cross Abstract: The integration of Large Language Models (LLMs) into Electronic Design Automation (EDA) and hardware security is rapidly reshaping the semiconductor i
arXiv:2605.08212v1 Announce Type: cross Abstract: There is an increasing number of algorithmic computations in theoretical physics. These, while conceptually simple, can nevertheless be time-consuming
arXiv:2605.08305v1 Announce Type: cross Abstract: Large Language Model (LLM) systems have been the frontier of AI in many application domains, leading to new challenges and opportunities for hyperpara
arXiv:2605.08850v1 Announce Type: cross Abstract: We design Local LMO - a new projection-free gradient-type method for constrained optimization. The key algorithmic idea is to replace the global linea
arXiv:2605.10777v1 Announce Type: new Abstract: The quality of open-weight language models has dramatically improved in recent years. Sharing weights greatly facilitates model adoption by enabling the
arXiv:2605.08545v1 Announce Type: new Abstract: Agent benchmarks typically report only final outcomes: pass or fail. This threatens evaluation credibility in three ways. First, scores may be inflated
arXiv:2509.20909v2 Announce Type: replace Abstract: Large language models (LLMs) are commonly evaluated on challenging benchmarks such as AIME and Math500, where benchmark contamination can make memor
arXiv:2605.10886v1 Announce Type: cross Abstract: Recent GPU generations deliver significantly higher FLOPs using lower-precision arithmetic, such as FP8. While successfully applied to large language
arXiv:2605.05812v2 Announce Type: replace Abstract: Off-policy, value-based reinforcement learning methods such as Q-learning are appealing because they can learn from arbitrary experience, including
arXiv:2605.09830v1 Announce Type: cross Abstract: We present Loom, an outfit recommendation system that combines neural embedding retrieval with structured domain scoring to generate complete, coheren
arXiv:2605.09948v1 Announce Type: new Abstract: Current Vision-Language-Action (VLA) models typically treat the deepest representation of a vision-language backbone as universally optimal for action p
arXiv:2605.09156v1 Announce Type: cross Abstract: The diachronic evolution from Latin to the Romance languages involved a restructuring of the grammatical gender system from a tripartite configuration
arXiv:2605.08787v1 Announce Type: new Abstract: Recent advances in 3D medical vision-language models have enabled joint reasoning over volumetric images and text, showing strong performance in medical