Knowledge catalogue
arXiv:2606.31602v1 Announce Type: new Abstract: This work presents Dual-Embedding Watermarking (DEW), a semantic watermarking scheme for large language models (LLMs) that leverages contextual and toke
arXiv:2606.31494v1 Announce Type: cross Abstract: Humans and animals exhibit remarkable robustness in physical manipulation, yet robots remain far behind. Progress toward human-level manipulation robu
arXiv:2606.31320v1 Announce Type: new Abstract: Safe online reinforcement learning requires policies to respect safety constraints while maintaining smooth optimization dynamics. Existing approaches t
arXiv:2606.30893v1 Announce Type: new Abstract: Multi-robot systems must simultaneously optimize competing objectives while maintaining coordinated behavior. Existing multi-agent reinforcement learnin
arXiv:2606.31719v1 Announce Type: cross Abstract: In collaborative dialogue, shared perception does not guarantee shared interpretation. Mutual understanding must be established through interaction. W
arXiv:2606.30935v1 Announce Type: cross Abstract: While neural network control policies are powerful, their deployment on safety critical systems depends on ensuring that they obey strict constraints.
arXiv:2606.15054v2 Announce Type: replace Abstract: Sparse autoencoders (SAEs) detect features via inner product, so a feature's activation scales with both its directional alignment and the input's n
arXiv:2606.31347v1 Announce Type: new Abstract: The electrification of transportation through electric vehicles introduces new challenges for power grid management, such as increased peak demand, volt
arXiv:2603.24036v2 Announce Type: replace Abstract: 3D Gaussian Splatting (3DGS) enables real-time, photorealistic novel view synthesis, making it a highly attractive representation for model-based vi
arXiv:2606.31562v1 Announce Type: new Abstract: Stabilization learning is an interdisciplinary paradigm that bridges control theory and machine learning. Its core idea is to enable systems to adjust t
arXiv:2411.17936v2 Announce Type: replace-cross Abstract: Deep neural networks are highly vulnerable to adversarial perturbations, raising serious safety concerns in the real-world systems. While prio
arXiv:2606.17882v2 Announce Type: replace Abstract: Bridges between graph neural networks (GNNs) and logical formalisms have been established by fixing architectural choices, such as the types of aggr
arXiv:2606.30849v1 Announce Type: new Abstract: Diffusion Transformers (DiTs) have significantly advanced audio-driven portrait animation, but their high computational cost leads to substantial infere
arXiv:2606.31236v1 Announce Type: new Abstract: Tactile sensors provide critical information for contact-rich manipulation, yet tactile representations and policies remain tightly coupled to each spec
arXiv:2606.31268v1 Announce Type: cross Abstract: The growing demand for privacy-preserving data sharing has positioned synthetic data generation as a critical component of responsible AI workflows. D
arXiv:2606.30851v1 Announce Type: cross Abstract: Improving the reliability of large language models (LLMs) at inference time is a central challenge in structured reasoning tasks such as Text-to-SQL.
That day when @elonmusk starts to sound a bit like my 2023 TED Talk, which called for “a global, nonprofit organization to regulate the tech for the sake of democracy and our collective future.” Good
arXiv:2606.31121v1 Announce Type: new Abstract: Sequentially evolving LLM memory enables agents to reuse past experience, but existing systems usually deploy each locally generated memory update witho
arXiv:2606.31599v1 Announce Type: cross Abstract: Vision-language models (VLMs) combining reinforcement learning (RL) ignite remarkable progress in multimodal reasoning, yet still struggle with medica
arXiv:2604.04050v2 Announce Type: replace Abstract: Flow-matching methods for 3D shape assembly learn point-wise velocity fields that transport parts toward assembled configurations, yet they receive
arXiv:2602.02124v2 Announce Type: replace-cross Abstract: Drug-induced toxicity is a leading cause of preclinical and early-clinical failure, making early detection critical. Histopathology is the gol
arXiv:2504.12557v3 Announce Type: replace-cross Abstract: Ensuring safe behavior in reinforcement learning (RL) is challenging when safety constraints are implicit and cannot be densely measured. In m
arXiv:2606.30887v1 Announce Type: cross Abstract: Large language models show promise for mental health support, yet therapeutic quality improves only when evaluation functions as an actionable control
arXiv:2606.31184v1 Announce Type: cross Abstract: Adaptive experiments for average treatment effects (ATE) require randomized allocations balancing valid inference with statistical efficiency. The ora
arXiv:2606.31976v1 Announce Type: new Abstract: Human-labeled data are widely used as reference annotations in ML, despite known variability across annotators in many expert-driven domains. In additio
arXiv:2606.32017v1 Announce Type: cross Abstract: Agentic reinforcement learning requires assigning credit to environment-facing actions such as searches, clicks, edits, navigation commands, and objec
arXiv:2606.31451v1 Announce Type: cross Abstract: Unified multimodal models (UMMs) have shown great promise in integrating understanding and generation across diverse modalities. However, existing res
arXiv:2606.31517v1 Announce Type: cross Abstract: Compared to supervised cross-modal hashing (CMH), unsupervised CMH reduces the reliance on manual labeling by learning binary codes from unlabeled ima
Ram Iyer / TechCrunch: Venice AI, which offers access to 200+ AI models while allowing users to retain their privacy, raised a 65M Series A led by Dragonfly at a 1B valuation — Concerns over the impac
arXiv:2606.31339v1 Announce Type: new Abstract: Agentic artificial intelligence is increasingly used to decompose industrial tasks, propose robot actions, and adapt execution plans in dynamic cyber-ph
arXiv:2603.16271v3 Announce Type: replace Abstract: Video diffusion models lack explicit geometric supervision during training, leading to inconsistency artifacts such as object deformation, spatial d
arXiv:2606.30698v1 Announce Type: new Abstract: Robotic-assisted endovascular interventions demand accurate, stable, and context-aware guidewire navigation in complex and patient-specific vascular ana
arXiv:2606.30989v1 Announce Type: cross Abstract: Warning: This paper contains several toxic and offensive statements. While reasoning generally improves fairness in recent large language models (LLMs
arXiv:2606.31043v1 Announce Type: new Abstract: Residual reinforcement learning adapts a pretrained robot policy by learning an additive correction to its actions. While effective when adaptation amou
arXiv:2606.31106v1 Announce Type: cross Abstract: Large-scale datasets and fast simulators have enabled improvements in driving policies that appear safe and robust, yet strong performance in nominal
Will the AI bubble pop is the wrong question. We partnered with Damon Cassidy, a video essayist with ~300k subscribers: even if it pops, the race to uncontrollable superintelligence doesn't go away. P
arXiv:2606.29911v1 Announce Type: new Abstract: Decision theory provides a formal framework for how agents should make choices under uncertainty, drawing on ideas from philosophy, probability, and cau
arXiv:2606.28525v1 Announce Type: cross Abstract: Fine-tuning on harmless data can partially undo behaviors acquired earlier in training. Safety can erode under benign post-alignment updates, unlearne
arXiv:2606.29273v1 Announce Type: cross Abstract: Emotion recognition of song lyrics is a challenging task since lyrics may not necessarily align with the overall emotion of a song. As a result, lyric
arXiv:2606.28943v1 Announce Type: new Abstract: Learning to bid in repeated multi-unit auctions with bandit feedback poses a fundamental challenge. Existing methods often rely on rigid explore-then-ex
arXiv:2606.29090v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has become the standard way to ground large language models in external knowledge, yet most systems retrieve a fi
arXiv:2603.12575v2 Announce Type: replace Abstract: Diffusion Transformers (DiTs) are a dominant backbone for high-fidelity text-to-image generation due to strong scalability and alignment at high res
arXiv:2606.29715v1 Announce Type: new Abstract: This paper presents an automatic system for recognizing pulmonary diseases in chest X-rays using geometric normalization of the lung region. The method
arXiv:2606.30072v1 Announce Type: new Abstract: Cooperative tasks in Multi-Agent Reinforcement Learning (MARL) require agents to collectively maximize a shared return. Under the Centralized Training w
arXiv:2606.30275v1 Announce Type: new Abstract: Home robots require reliable vital signs monitoring to support long-term companionship and safety in daily environments, yet obtaining respiration and h
arXiv:2606.29275v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) are typically trained under fixed context structures, restricting denoising to predetermined token subsets. This create
arXiv:2511.01472v2 Announce Type: replace Abstract: The rapid progress of vision--language models (VLMs) has sparked growing interest in robotic control, where natural language can express the operati
arXiv:2603.07744v2 Announce Type: replace Abstract: Precise object placement remains underexplored in aerial manipulation, where most systems rely on predefined target coordinates and focus primarily
arXiv:2606.28739v1 Announce Type: new Abstract: Large language models increasingly act as agents: they call tools, move money, delete records, and send messages on a user's behalf. To keep them safe,
arXiv:2606.28347v1 Announce Type: cross Abstract: Contemporary AI safety spans pre-training interventions, post-training alignment, deployment-time controls, monitoring, and red-teaming. These methods
arXiv:2604.00835v2 Announce Type: replace Abstract: Large language models are increasingly being deployed as autonomous agents yet their real world effectiveness depends on reliable tools for informat
arXiv:2606.28331v1 Announce Type: cross Abstract: The widespread deployment of generative artificial intelligence (AI) models has raised serious concerns about the proliferation of AI-generated conten
arXiv:2606.28881v1 Announce Type: cross Abstract: Predicting student performance and characterizing metacognitive calibration are essential for personalization in intelligent tutoring systems. Prior r
arXiv:2606.29774v1 Announce Type: new Abstract: Long-horizon embodied manipulation requires agents to remember persistent objects, track changing scene states, and reuse prior interaction knowledge. H
arXiv:2606.20470v2 Announce Type: replace-cross Abstract: Agentic AI systems increasingly rely on language-model components to interpret instructions, process external data, invoke tools, and coordina
Choosing the threshold of an alert policy can be a headache. You have to analyze historical data, aggregate it into semantically meaningful time series, and choose a threshold that matters. If the wor
arXiv:2606.29209v1 Announce Type: cross Abstract: We present AnyBody, a unified whole-body humanoid controller driven by an arbitrary subset of body keypoints chosen at deploy time. Prior physics-base
arXiv:2606.29792v1 Announce Type: new Abstract: Human adults can often perform a novel task correctly on the first attempt after only receiving verbal or written instructions. This rapid instructed ta
arXiv:2606.29985v1 Announce Type: new Abstract: Diversity in LLM mathematical reasoning is critical for exploration, but common diversity metrics mostly capture surface-level variation rather than dif
arXiv:2601.20336v5 Announce Type: replace-cross Abstract: Do the functional narratives in cryptocurrency whitepapers correspond to how their tokens behave in markets? We develop a content-verified, co