Safe-RULE: Safe Reinforcement UnLEarning
arXiv:2606.09559v1 Announce Type: cross Abstract: Offline safe reinforcement learning (Safe RL) enables policy learning without online interactions, making it suitable for safety-critical systems such
Knowledge catalogue
arXiv:2606.09559v1 Announce Type: cross Abstract: Offline safe reinforcement learning (Safe RL) enables policy learning without online interactions, making it suitable for safety-critical systems such
arXiv:2606.08037v1 Announce Type: cross Abstract: Electrocardiogram (ECG) classification models often suffer from severe label scarcity, making semi-supervised learning (SSL) an attractive strategy fo
arXiv:2606.07874v1 Announce Type: new Abstract: LLMs-as-judges are the only way to evaluate safety at scale. Despite their importance, LLM-judges themselves are rarely evaluated beyond human agreement
arXiv:2606.09009v1 Announce Type: new Abstract: Vision-Language-Action models face significant challenges in real-world deployment due to the entanglement of high-level reasoning with low-level contro
arXiv:2606.08797v1 Announce Type: cross Abstract: Decision-focused learning has shown great promise for addressing predict-then-optimize problems, particularly in the presence of under-specified model
arXiv:2606.09377v1 Announce Type: cross Abstract: Formal neural network verification -- proving that a network satisfies safety properties for all inputs in a specified domain -- is bounded in practic
arXiv:2606.08402v1 Announce Type: cross Abstract: Generating complete 3D scenes from a single image requires inferring globally consistent geometry, object relationships, and environmental context fro
arXiv:2606.08206v1 Announce Type: new Abstract: We present SegmentAnyTreeV2, a sensor- and platform-agnostic framework for semantic and instance segmentation of forest point clouds. The model combines
arXiv:2606.09304v1 Announce Type: cross Abstract: On-policy distillation (OPD) trains a student on its own trajectories with dense per-token supervision from a stronger teacher, and often outperforms
arXiv:2606.07596v1 Announce Type: new Abstract: Fine-tuning often introduces spurious correlations alongside task knowledge, causing systematic failures on underrepresented groups. Existing mitigation
arXiv:2603.22793v2 Announce Type: replace Abstract: Classroom AI systems increasingly infer high-level educational states such as engagement, confusion, collaboration, participation, and instructional
arXiv:2606.08671v1 Announce Type: new Abstract: Agent skills extend language-model agents with task-specific procedures, scripts, and references, but the tasks and environments they target continually
arXiv:2606.08332v1 Announce Type: new Abstract: Self-supervised learning (SSL) has achieved remarkable representation learning performance, but many existing methods rely on large batch sizes, memory
arXiv:2606.08372v1 Announce Type: cross Abstract: Synthetic data is increasingly promoted as a privacy-preserving substitute for releasing sensitive tabular records, yet its central adversarial threat
arXiv:2601.23231v2 Announce Type: replace-cross Abstract: Flow-based generative models provide strong unconditional priors for inverse problems, but guiding their dynamics for conditional generation r
arXiv:2603.19183v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models have emerged as a promising approach for general-purpose robot manipulation. However, little research has mechan
arXiv:2606.08382v1 Announce Type: cross Abstract: Low-rank projection has emerged as a promising approach for compressing the KV cache by exploiting hidden-dimension redundancy. However, prior methods
arXiv:2606.07565v1 Announce Type: new Abstract: Intelligent scaling of microservices in cloud platforms is crucial for mitigating escalating compute costs while avoiding service disruptions. Current s
arXiv:2606.07647v1 Announce Type: new Abstract: Large vision language models (LVLMs) have made rapid advancements and are deployed across various applications, yet hallucinations remain a major challe
arXiv:2512.03470v5 Announce Type: replace Abstract: A key challenge in infrared small target detection (IRSTD) is that weak target signal responses are easily obscured by strong background clutter, fr
arXiv:2606.09547v1 Announce Type: new Abstract: Learning everyday skills, like cooking a dish, relies increasingly on instructional media such as online videos. This opens the door to the use of video
arXiv:2606.07689v1 Announce Type: new Abstract: Deep research agents have attracted increasing attention for their ability to collect large-scale online information to acquire target knowledge, with r
arXiv:2606.07615v1 Announce Type: cross Abstract: Deep neural networks often contain redundant hidden units. Removing individual weights can reduce parameter count, but unstructured sparsity is not al
arXiv:2606.08451v1 Announce Type: cross Abstract: Safety-aligned large language models often exhibit sycophancy, which is the tendency to affirm users' opinions regardless of factual accuracy. Althoug
arXiv:2606.09248v1 Announce Type: new Abstract: Multi-modal Large Language Models (MLLMs) have achieved remarkable progress in video temporal grounding with reinforcement learning for generating reaso
Elon Musk posted on X about Tesla's AI chip design engineering team and their work on the AI6 chip, expressing confidence in the team's performance and suggesting the chip could achieve notable capabi
arXiv:2606.08231v1 Announce Type: new Abstract: Test-time Scaling (TTS) has emerged as a pivotal research direction for enhancing model performance by dynamically allocating computational resources du
arXiv:2606.07897v1 Announce Type: new Abstract: Current AI models frequently exhibit epistemic sycophancy, endorsing claims to agree with a user. Existing evaluations typically measure this either by
arXiv:2606.07950v1 Announce Type: new Abstract: RL with verifiable rewards can substantially improve LLM reasoning, yet standard GRPO-style training often treats easy, hard, and learnable questions al
arXiv:2606.07861v1 Announce Type: cross Abstract: Recent vision-language models (VLMs) excel at multimodal understanding and reasoning, yet their fine-grained visual perception remains underexplored.
arXiv:2606.07562v1 Announce Type: cross Abstract: RNA design consists of discovering a nucleotide sequence that optimizes predefined criteria, such as secondary structure. It is useful for synthetic b
arXiv:2606.07587v1 Announce Type: new Abstract: LLM routing has become a popular approach to improve the cost-quality trade-off of LLM services by dynamically selecting a model for each query. Recent
arXiv:2601.04805v2 Announce Type: replace Abstract: Large reasoning models (LRMs) have attracted much attention due to their exceptional performance. However, their performance mainly stems from think
arXiv:2606.08719v1 Announce Type: new Abstract: ''Thinking with Images'' has emerged as an effective paradigm for fine-grained visual reasoning: by explicitly zooming into relevant regions and reasoni
arXiv:2606.08260v1 Announce Type: new Abstract: Recent advances in Diffusion Transformers have driven rapid progress in video generation and editing, yet these capabilities are still handled by separa
arXiv:2606.07520v1 Announce Type: cross Abstract: Instruction Following (IF) is a core capability of LLMs, requiring strict adherence to diverse constraints, ranging from verifiable ones (e.g., output
arXiv:2606.09806v1 Announce Type: cross Abstract: We introduce Topological Neural Operators (TNOs), a principled framework for operator learning on cell complexes that lifts neural operators (NOs) fro
arXiv:2601.15727v3 Announce Type: replace Abstract: The performance of modern AI systems is fundamentally constrained by the quality of their underlying GPU kernels, which translate high-level algorit
arXiv:2606.08633v1 Announce Type: new Abstract: Long-horizon maritime trajectory prediction is important for shipping management, logistics planning, and maritime risk analysis, yet month-level foreca
arXiv:2511.05017v2 Announce Type: replace Abstract: Hallucinations in Large Vision-Language Models (LVLMs) remain a persistent challenge, often stemming from inadequate integration of visual informati
arXiv:2603.25184v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become essential for post-training large language models (LLMs) in reasoning tasks. While scaling rollouts can
arXiv:2606.07581v1 Announce Type: cross Abstract: A modern post-training pipeline often writes one symbol for its policy, pi_theta, while evaluating it through two different programs: a training kerne
arXiv:2606.08432v1 Announce Type: new Abstract: On-policy distillation (OPD) has become a central post-training tool for large language models (LLMs), providing dense per-token teacher supervision alo
arXiv:2606.09030v1 Announce Type: cross Abstract: Clinical early warning systems built on electronic health records, in which clinical observations are recorded as irregularly sampled medical time ser
arXiv:2606.07569v1 Announce Type: new Abstract: Accurate carbon emission monitoring is critical for climate policy and emerging regulatory mechanisms such as the EU Carbon Border Adjustment Mechanism,
arXiv:2606.08379v1 Announce Type: new Abstract: This study addresses the optimal execution of large stock sell programs by introducing TT-DAC-PS (Twin-Target Deterministic Actor-Critic with Policy Smo
arXiv:2606.09608v1 Announce Type: new Abstract: Diffusion-based generative models have achieved remarkable success in real-world image super-resolution (SR). With tiled diffusion techniques, these mod
arXiv:2606.08464v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning has proven effective for enhancing problem-solving in large language models. However, when applied to multimodal LLMs (
arXiv:2606.08775v1 Announce Type: cross Abstract: Visual world models have shown great potential in learning complex system dynamics. Recent advancements leverage these models as transition functions
arXiv:2606.07592v1 Announce Type: new Abstract: Offline reinforcement learning requires careful conservatism to mitigate distribution shift, yet most existing methods apply a fixed penalty uniformly a
arXiv:2606.08032v1 Announce Type: cross Abstract: Reinforcement Learning from Human Feedback via Proximal Policy Optimization often suffers from policy mode collapse, brittle exploration loops, and di
arXiv:2510.03244v2 Announce Type: replace-cross Abstract: Large time series foundation models often adopt channel-independent architectures to handle varying data dimensions, but this design ignores c
arXiv:2509.09151v2 Announce Type: replace-cross Abstract: Research in video understanding has advanced rapidly, driven by increasingly diverse datasets and more powerful model architectures. While exi
arXiv:2606.07872v1 Announce Type: new Abstract: When a multimodal large language model answers a visual reasoning question correctly, is the prediction actually supported by the task-critical visual e
arXiv:2606.07595v1 Announce Type: cross Abstract: Vision-language agents increasingly consume screenshots, documents, and user interfaces before writing to memory, sending messages, or invoking extern
arXiv:2606.08094v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies are typically shipped as Python/PyTorch stacks that assume a workstation-class GPU, a mismatch for the hardware
arXiv:2606.07723v1 Announce Type: new Abstract: Open-vocabulary long-horizon manipulation requires robots to reason over flexible instructions and complex multi-object scenes while adaptively planning
arXiv:2606.08030v1 Announce Type: cross Abstract: Agentic tutoring systems introduce a coordination challenge: multiple agents may propose different but reasonable interventions, yet only one response
arXiv:2606.07687v1 Announce Type: cross Abstract: Video world models are increasingly used to provide predictive visual representations, yet it remains unclear which pretraining signals induce action-
arXiv:2606.08239v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have made substantial advancements in video understanding, yet the reliability of their responses remains under