Knowledge catalogue
arXiv:2605.28639v1 Announce Type: cross Abstract: Instruction-based suppression is widely used to prevent language models from generating prohibited content, yet it remains unclear whether suppression
arXiv:2605.28464v1 Announce Type: cross Abstract: Legal Judgment Prediction (LJP) has become a core benchmark for evaluating AI in the criminal legal domain, but it only sees criminal cases that have
arXiv:2605.27381v1 Announce Type: cross Abstract: Claims about recursive self-improvement in AI often slide from repeated internal revision to the possibility of qualitatively stronger capability with
arXiv:2605.28498v1 Announce Type: cross Abstract: Conversational artificial intelligence (AI) provides an efficient and convenient gateway to information access. However, it can cause overreliance whe
arXiv:2605.27599v1 Announce Type: cross Abstract: Agentic AI workloads - where a single user goal triggers multi-step orchestration, tool calls, retries, and failure recovery - are being targeted for
arXiv:2605.28647v1 Announce Type: new Abstract: It is well known that LLM guardrails and trained persona dynamics can produce a reality gap: the distance between the world a LLM is permitted or shaped
arXiv:2605.27901v1 Announce Type: cross Abstract: Chain-of-thought (CoT) monitoring has been proposed as a promising safety mechanism for detecting misaligned behavior in large language models. Howeve
arXiv:2605.27557v1 Announce Type: new Abstract: Card payment fraud detection is usually framed as a supervised classification problem. Although this approach has generated practical progress, improvem
arXiv:2605.27564v1 Announce Type: cross Abstract: Language models are becoming the default interface to factual knowledge, yet they often verify outputs more reliably than they generate them. This gen
arXiv:2601.19926v2 Announce Type: replace-cross Abstract: We present a systematic review of 337 articles evaluating the syntactic abilities of Transformer-based language models (TLMs), reporting on ov
arXiv:2605.28190v1 Announce Type: new Abstract: Embedding benchmarks like MTEB report a single score per model, implicitly treating robustness as a static, scalar property. We argue that embedding rob
arXiv:2605.28210v1 Announce Type: new Abstract: Drawing on Ullmann-Margalit's concept of opting (transformative, irrevocable, and shadowed by foreclosed alternatives), we show that current AI systems
arXiv:2605.28700v1 Announce Type: new Abstract: The GSM-Symbolic benchmark (Mirzadeh et al., 2025) reported consistent performance drops across 25 Large Language Models (LLMs) when tested on template-
arXiv:2605.28020v1 Announce Type: new Abstract: With the rapid progress of large language models (LLMs), reliably evaluating the capabilities of pre-trained LLMs has become increasingly important. The
arXiv:2602.15515v2 Announce Type: replace-cross Abstract: Training against white-box deception detectors has been proposed as a way to make AI systems honest. However, such training risks models learn
arXiv:2601.01496v2 Announce Type: replace-cross Abstract: In this paper, we settle the problem of learning optimal linear contracts from data in the offline setting, where agent types are drawn from a
arXiv:2504.04540v2 Announce Type: replace-cross Abstract: 3D Large Language Models (LLMs) leveraging spatial information in point clouds for 3D spatial reasoning attract great attention. Despite some
arXiv:2510.21890v2 Announce Type: replace-cross Abstract: This book presents the core principles that have guided the development of diffusion models, tracing their origins and showing how diverse for
arXiv:2601.17737v3 Announce Type: replace-cross Abstract: Recent advances in video generation have produced models capable of synthesizing stunning visual content from simple text prompts. However, th
arXiv:2605.27965v1 Announce Type: new Abstract: Reasoning models often generate long traces in which useful self-correction and unproductive revision are hard to distinguish. We study this distinction
arXiv:2510.20665v3 Announce Type: replace Abstract: Evaluating the quality of reasoning traces from large language models remains understudied, labor-intensive, and unreliable: current practice relies
arXiv:2602.14862v2 Announce Type: replace-cross Abstract: Temperature scaling is a simple method that allows to control the uncertainty of probabilistic models. It is mostly used in two contexts: impr
arXiv:2605.28594v1 Announce Type: cross Abstract: In this article, we present an improved version of the PULSE method (Partition function Unsupervised Learning Sampling and Evaluation) for estimating
arXiv:2605.28713v1 Announce Type: new Abstract: Context compression aims to shorten long context inputs with minimal information loss for LLM inference acceleration. While existing methods have shown
arXiv:2605.28589v1 Announce Type: new Abstract: Several important learning tasks can be formulated as minimizing an entropy-regularized objective over an appropriate space of probability distributions
arXiv:2512.09786v2 Announce Type: replace Abstract: Examples of embedded intelligence include a wide variety of tiny neural networks used on-board wireless sensors and actuators, which are expected to
arXiv:2605.28557v1 Announce Type: cross Abstract: LLMs are increasingly used for software modernization, code translation, and database migration. However, LLM-based Oracle2PostgreSQL migration remain
arXiv:2605.28000v1 Announce Type: cross Abstract: Large language model agents are increasingly expected to perform operational work: calling APIs, manipulating files, assembling workflows, and acting
arXiv:2508.14082v3 Announce Type: replace Abstract: Semi-supervised regression (SSR), which aims to predict continuous scores for samples while reducing the reliance on large-scale labeled data, has r
arXiv:2605.28348v1 Announce Type: new Abstract: Vision-language segmentation models have recently achieved strong performance by leveraging high-level semantic object categories expressed in natural l
arXiv:2603.04631v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly integrated into critical decision-making pipelines, a trend that raises the demand for robust and auto
arXiv:2605.27879v1 Announce Type: new Abstract: Explainable AI (XAI) helps users interpret model behavior and identify potential faults. Agentic XAI systems use Large Language Models (LLMs) to make ex
arXiv:2605.28710v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for the automatic evaluation of generated text, yet most prior work focuses on English. Despite the
arXiv:2605.27894v1 Announce Type: new Abstract: Video-Language Models (VLMs) have demonstrated impressive multi-modal reasoning capabilities across diverse computer vision applications. However, these
arXiv:2605.28699v1 Announce Type: new Abstract: Large language models increasingly rely on either reinforcement learning or multi-agent prompting to improve reasoning, yet these two paradigms remain d
arXiv:2605.27690v1 Announce Type: new Abstract: LLM agents increasingly operate through multi-turn tool use and environment interaction, where safety risks often emerge from intermediate steps long be
arXiv:2605.28102v1 Announce Type: new Abstract: Large language models trained with Reinforcement Learning from Human Feedback (RLHF) and Constitutional AI exhibit persistent behavioral patterns that s
arXiv:2605.28331v1 Announce Type: new Abstract: Transfer learning makes it possible to use large vision networks on a variety of domains, by specializing their models' general filters to new tasks. Ho
arXiv:2601.21309v4 Announce Type: replace Abstract: The increasing scale of graph datasets has significantly improved the performance of graph representation learning methods, but it has also introduc
arXiv:2605.27659v1 Announce Type: cross Abstract: Due to limited resources and public safety concerns, deep reinforcement learning (RL) agents for many cyber-physical systems (e.g., autonomous vehicle
arXiv:2605.28600v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting substantially improves the sample efficiency of transformers, reducing the complexity of tasks like parity learning fro
arXiv:2605.28566v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities, yet their standard generation process -- auto-regressive token predict
arXiv:2605.27478v1 Announce Type: cross Abstract: We introduce Triangular-Reference Schrodinger Bridges for Time Series (TR-SBTS), a conservative extension of the SBTS framework in which the Brownian
arXiv:2605.27644v1 Announce Type: cross Abstract: Terrain understanding is fundamental for mobile robots operating in unstructured outdoor environments. Existing vision-based traversability estimation
arXiv:2601.13433v3 Announce Type: replace Abstract: Prior research demonstrates that performance of language models on reasoning tasks can be influenced by suggestions, hints and endorsements. However
arXiv:2602.02417v2 Announce Type: replace Abstract: Continual learning aims to acquire tasks sequentially without catastrophic forgetting, yet standard strategies face a core tradeoff: regularization-
arXiv:2605.27817v1 Announce Type: cross Abstract: Video generative models have emerged as a promising robotics backbone, capable of generating videos that depict the completion of complex tasks across
arXiv:2506.08311v2 Announce Type: replace-cross Abstract: Automated Program Repair (APR) agents leverage Large Language Models (LLMs) to autonomously diagnose and fix software bugs through reasoning,
arXiv:2605.28705v1 Announce Type: new Abstract: In-context learning (ICL) derives its power from enabling Large Language Models to adapt to new tasks via prompt-based reasoning alone, entirely bypassi
arXiv:2605.27582v1 Announce Type: cross Abstract: Embodied navigation requires an agent to map language and visual observations to a stream of spatial actions that drive a real robot through environme
arXiv:2605.28165v1 Announce Type: new Abstract: The literature has proposed various robust alternatives to empirical risk minimisation to address failure modes such as distribution shift, label noise
arXiv:2602.13075v2 Announce Type: replace Abstract: Graph pre-training has achieved remarkable success in recent years, delivering transferable representations for downstream adaptation. However, most
arXiv:2605.28063v1 Announce Type: cross Abstract: Audio generation has made significant progress, yet synthesizing unified audio where speech and sounds are naturally composited remains a challenge. C
arXiv:2404.06106v3 Announce Type: replace Abstract: Low dimensional structures appear ubiquitously in the eigenspectra of deep learning matrices in classification networks trained in the overparameter
arXiv:2605.27767v1 Announce Type: cross Abstract: Recent advances in large language models have enabled natural language to serve as a flexible interface for controlling complex systems, but often at
arXiv:2605.27740v1 Announce Type: new Abstract: Long-context inference in large language models (LLMs) is bottlenecked by the linear growth of the self-attention key-value (KV) cache. Top-k sparse att
arXiv:2605.28507v1 Announce Type: new Abstract: Recent work on the sequence universality of State Space Models (SSMs) has introduced efficient, maximally expressive continuous-time approaches for time
arXiv:2605.27376v1 Announce Type: cross Abstract: While prompt-based text-to-speech (TTS) models enable natural language-driven speaking style control, they often provide limited fine-grained control
arXiv:2605.27676v1 Announce Type: cross Abstract: Fine-tuning a pretrained language model on a curated dataset can produce spurious correlations between the fine-tuning task and unintended latent fact
arXiv:2605.27721v1 Announce Type: cross Abstract: Understanding what a user believes and intends is central to building effective agent assistants. This ability is often evaluated through Theory-of-Mi