Search: “safety”

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: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: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: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: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: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:2605.28733v1 Announce Type: new Abstract: Product images strongly influence consumer decision-making in online marketplaces. Empowered by multimodal contrastive learning, generative AI can outpu

arXiv:2605.28023v1 Announce Type: cross Abstract: Visual captioning requires models to capture visual content faithfully while minimizing both omission and hallucination. As the dominant paradigm for

arXiv:2605.28565v1 Announce Type: cross Abstract: Users of search-augmented LLMs rely on citations as evidence that responses are grounded in real sources, and rarely verify the cited pages themselves

arXiv:2605.28186v1 Announce Type: cross Abstract: Deep reinforcement learning (DRL) has been shown to achieve high performance on locomotion control tasks in MuJoCo benchmarks such as HalfCheetah, Ant

arXiv:2605.28818v1 Announce Type: new Abstract: Large language models (LLMs) have become increasingly useful computational models of human language processing, but it remains unclear whether vision-la

arXiv:2601.07648v2 Announce Type: replace Abstract: As Natural Language Generation (NLG) dominates modern NLP, scalable evaluation remains a critical bottleneck. Consequently, LLM-as-a-judge (LaaJ) ad

arXiv:2605.28527v1 Announce Type: new Abstract: Vision--language--action (VLA) policies are trained to imitate actions; their loss never asks them to estimate reward, progress, or future success. Thei

arXiv:2602.02855v2 Announce Type: replace Abstract: Pre-training on a source task is usually expected to facilitate fine-tuning on similar downstream problems. In this work, we mathematically show tha

arXiv:2605.28295v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) trains reasoning models without labeled trajectories, relying on grouped rollouts to expose the po

arXiv:2605.21743v2 Announce Type: replace Abstract: Conversation logs from AI platforms are increasingly used to measure occupational exposure to artificial intelligence, but the users observed in the

arXiv:2503.18893v2 Announce Type: replace Abstract: Long-context Large Language Models (LLMs) enable powerful applications but incur high memory costs due to the key-value states (KV-Cache). Recent st

arXiv:2605.26174v1 Announce Type: cross Abstract: Production language-model systems answer a request by partitioning it across an invisible orchestration of worker agents that recompose one integrated

arXiv:2605.27095v1 Announce Type: new Abstract: Learning from demonstrations in embodied control is often cast as behavioral cloning, and recent diffusion or flow-matching policies improve this paradi

arXiv:2511.07667v2 Announce Type: replace Abstract: The equitable assessment of individual contribution in teams remains a persistent challenge, where conflict and disparity in workload can result in

arXiv:2605.25763v2 Announce Type: replace Abstract: Text-to-image synthesis has made significant progress, benefiting from the strong generative capabilities of diffusion models. However, these models

arXiv:2605.26130v1 Announce Type: new Abstract: Operational weather prediction at kilometer scales remains computationally prohibitive for traditional numerical weather prediction (NWP) models, limiti

arXiv:2511.16870v3 Announce Type: replace Abstract: Enforcing alignment between the internal representations of diffusion or flow-based generative models and those of pretrained self-supervised encode

arXiv:2506.23149v2 Announce Type: replace Abstract: Reusable skills play a key role in improving LLM-based agents, but existing skill-evolution methods often fail to ensure that evolved skills both co

arXiv:2605.26552v1 Announce Type: cross Abstract: Aligning a few-step generative model is challenging, since existing alignment frameworks typically rely on restrictive assumptions: a tractable likeli

arXiv:2603.17218v2 Announce Type: replace-cross Abstract: Post-training alignment optimizes language models to match human preference signals, but this objective is not equivalent to modeling observed

arXiv:2605.27355v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) is the standard method to align Large Language Models (LLMs) with human preferences. In this work, we

arXiv:2605.26442v1 Announce Type: cross Abstract: Much of the alignment tuning literature is organized around optimization objectives, while the construction of alignment data is often treated implici

arXiv:2605.26397v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used in decision-making tasks where they can amplify or suppress perspectives, raising concerns in high-

arXiv:2605.26434v1 Announce Type: cross Abstract: EEG foundation models, pre-trained on large-scale unlabelled EEG data, have emerged as a promising direction towards learning generalizable EEG repres

arXiv:2601.05028v2 Announce Type: replace Abstract: Equivariance is a powerful inductive bias in neural networks, improving generalisation and physical consistency. Recently, however, non-equivariant

arXiv:2506.09532v5 Announce Type: replace-cross Abstract: We present Athena-PRM, a multimodal process reward model (PRM) designed to evaluate the reward score for each step in solving complex reasonin

arXiv:2605.26559v1 Announce Type: cross Abstract: Tabular foundation models achieve strong accuracy on choice prediction tasks, but their predictions often violate the economic logic those tasks requi

arXiv:2605.27110v1 Announce Type: cross Abstract: In this work, we propose BAIT (Boundary-Aware Iterative Trap), a three-step jailbreak framework that approaches malicious goals through internal discl

arXiv:2605.27293v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has become a standard recipe for improving the reasoning abilities of large language models. Existing alg

arXiv:2603.03585v2 Announce Type: replace-cross Abstract: Misinformation is a growing societal threat, and susceptibility to misinformative claims varies across demographic groups due to differences i

arXiv:2601.03525v3 Announce Type: replace-cross Abstract: Effective reward design is a central challenge in Reinforcement Learning (RL) for code generation. Mainstream test-suite-level outcome rewards

arXiv:2605.26491v1 Announce Type: cross Abstract: Preference optimization has emerged as an efficient alternative to online reinforcement learning from human feedback (RLHF) for aligning text-to-image

arXiv:2605.27131v1 Announce Type: cross Abstract: Enterprise data platforms face an enduring tension between domain self-service and holistic governance. The data mesh paradigm proposed decentralized

arXiv:2605.26684v1 Announce Type: cross Abstract: Group-based reinforcement learning (RL) methods have achieved remarkable success in improving the performance of large language models (LLMs) and have

arXiv:2605.26654v1 Announce Type: cross Abstract: Reinforcement learning (RL) often has a hierarchical structure, where an upper-level (UL) learner selects model parameters and a lower-level (LL) deci

arXiv:2605.26182v1 Announce Type: new Abstract: Generating physically buildable brick structures from 3D shapes requires more than geometric reconstruction: the output must also satisfy discrete part

arXiv:2511.14075v2 Announce Type: replace-cross Abstract: Classifier free guidance is a standard method for conditional sampling in diffusion models, but its sampling rule is not aligned with the obje

arXiv:2605.26657v1 Announce Type: new Abstract: Long-horizon decision problems with cumulative damage couple locally attractive actions to globally adverse outcomes. We identify two orthogonal failure

arXiv:2605.26990v1 Announce Type: cross Abstract: Bayesian experimental design (BED) is a principled framework for data-efficient design of sequential experiments. However, existing BED methods are un