Knowledge catalogue
arXiv:2608.24858v1 Announce Type: new Abstract: Marginalized importance weighting evaluates a target policy by reweighting offline state-action samples with its discounted occupancy ratio, characteriz
Bill Gates / GatesNotes: Bill Gates says “the AI era will be one of the most turbulent times in human history” and “we are not preparing adequately”, calling for a regulatory framework — Bill Gates, a
arXiv:2608.24823v1 Announce Type: new Abstract: Spatially resolved biology requires representations that preserve biological neighborhood structure rather than only exact cross-modal correspondences.
Breaking news: OpenAI admitted its internal monitoring system was not triggered until more than a week after its AI agents broke free of controls, accessed the internet and hacked start-up Hugging Fac
arXiv:2608.24372v1 Announce Type: new Abstract: AI-generated image quality assessment (AIGIQA) requires jointly reasoning about perceptual fidelity and prompt alignment, two quality dimensions that ar
arXiv:2608.24217v1 Announce Type: new Abstract: We propose CARO, a contact-agnostic residual observation framework for policy adaptation. CARO embeds a fixed-base Euler--Lagrange model into the reinfo
arXiv:2608.24303v1 Announce Type: new Abstract: Transitioning from bespoke time series models towards time series foundation models changes the relationship of model and application from one-to-one to
arXiv:2608.23939v1 Announce Type: new Abstract: Offline reinforcement learning is intrinsically multi-objective: a policy must remain compatible with the behavioral support of a fixed dataset while pr
Confirming what we already knew: The OpenAI Hugging Face incident would have been prevented had OpenAI been monitoring the agents in any meaningful way. This wasn't a hard technical problem. It was an
arXiv:2510.14249v2 Announce Type: replace-cross Abstract: Understanding and modeling the relationship between language and sound are essential for applications such as music information retrieval, tex
arXiv:2608.24885v1 Announce Type: cross Abstract: Action-conditioned world models are increasingly used as learned simulators for policy evaluation and improvement, yet their effectiveness rests on an
arXiv:2608.23924v1 Announce Type: cross Abstract: Repetitive maritime operations can be effectively learned using the Imitation Learning (IL) paradigm, which transfers human expertise directly to Unma
arXiv:2601.19969v2 Announce Type: replace-cross Abstract: Human-in-the-loop guidance has emerged as an effective approach for accelerating online reinforcement learning (RL) in real-world manipulation
arXiv:2608.24274v1 Announce Type: new Abstract: A sustainable diet represents a multi-dimensional synergy among four essential pillars: nutrition adequacy, economic affordability, cultural acceptabili
arXiv:2608.23848v1 Announce Type: new Abstract: Budget-constrained agentic search arises when an LLM agent must refine candidates under a small evaluation budget, because validation is expensive, gene
arXiv:2410.18321v3 Announce Type: replace-cross Abstract: Confidence calibration matters wherever a classifier's probabilities, not just its labels, are consumed downstream. We study Focal Calibration
arXiv:2603.01113v2 Announce Type: replace Abstract: Interactive task planning with large language models (LLMs) lets robots generate high-level action plans from natural language, but over long horizo
arXiv:2608.24368v1 Announce Type: new Abstract: Reliable multi-turn tool use requires an agent to preserve an evolving task state and ensure that each action remains consistent with it. However, direc
arXiv:2608.24121v1 Announce Type: new Abstract: Radiology report generation (RRG) has recently benefited from large language models, which substantially improve report fluency. However, clinically fai
arXiv:2608.23921v1 Announce Type: new Abstract: Recent Vision-Language Models encode high-resolution images into long visual token sequences, incurring prohibitive prefill costs. To compress them, exi
COMPASS is a scalable cross‑embodiment robot navigation framework that builds on NVIDIA’s X‑Mobility pretrained policies, adding lightweight RL fine‑tuning specialists for new robot‑scene pairs to avo
arXiv:2608.24588v1 Announce Type: new Abstract: Large Language Model (LLM) agents increasingly solve long-horizon tasks through multi-turn interactions with users and external tools. In these settings
I'm glad OpenAI let you do this, but damnit this was way too small of an investigation team and way too narrowly scoped! --They were only allowed to investigate activity that took place from July 7-13
arXiv:2608.24471v1 Announce Type: new Abstract: Maritime moving-target observation scheduling with agile Earth observation satellites is a dynamic, sequence-dependent combinatorial optimization proble
arXiv:2608.23887v1 Announce Type: new Abstract: Latent-conditioned adaptive policies can control robots across changing dynamics, but their learned latents remain internal representations of the polic
arXiv:2608.24429v1 Announce Type: cross Abstract: Unsupervised domain adaptation (UDA) has been widely concerned in the fields of machine learning, pattern recognition, and computer vision. Traditiona
arXiv:2608.24571v1 Announce Type: new Abstract: Tool-augmented language models are bounded by the APIs humans bothered to write; existing tool-creation systems patch this by prompting a frozen LLM at
arXiv:2505.23462v2 Announce Type: replace Abstract: Blind face restoration from low-quality images is a challenging task that requires not only high-fidelity image reconstruction, but also preservatio
arXiv:2604.01597v2 Announce Type: replace Abstract: Traditional RL algorithms like Proximal Policy Optimization (PPO) typically train on the entire rollout buffer, operating under the assumption that
arXiv:2608.23831v1 Announce Type: cross Abstract: While reinforcement learning (RL) allows generalist robot policies to continually improve during deployment, the large model size of modern generalist
arXiv:2608.24795v1 Announce Type: new Abstract: Recently, the rapid advancement of multimodal domains has driven a data-centric paradigm shift in graph ML, transitioning from text-attributed to multim
arXiv:2608.24156v1 Announce Type: cross Abstract: Industrial actor--critic methods usually represent continuous actions as anonymous numerical coordinates. They must therefore learn from limited inter
arXiv:2608.23853v1 Announce Type: new Abstract: The interpretation of endoscopic imagery in ulcerative colitis is complex and subjective, with variability in human assessment and subtle mucosal inflam
arXiv:2608.24065v1 Announce Type: cross Abstract: While recent advances in data synthesis aim to curate high-quality datasets, most generation pipelines still rely on heuristic prompt-based control. T
arXiv:2608.24342v1 Announce Type: cross Abstract: Synthetic image generation is a promising strategy to address data scarcity and the underrepresentation of clinically important phenotypes in medical
arXiv:2608.24214v1 Announce Type: new Abstract: Agentic retrieval-augmented generation (RAG) requires language models to decide when to continue searching and when to answer. Existing RL-based methods
arXiv:2608.23830v1 Announce Type: cross Abstract: RL has emerged as a powerful paradigm for enhancing the instruction following capabilities of LLMs. While existing training recipes achieve substantia
arXiv:2510.07289v2 Announce Type: replace Abstract: Molecular graph representation learning is widely used in chemical and biomedical research. While pre-trained 2D graph encoders have demonstrated st
arXiv:2608.24400v1 Announce Type: cross Abstract: We study multilevel fair resource allocation with tree-structured hierarchical relations among agents. At each level, the problem can be viewed locall
arXiv:2604.04407v2 Announce Type: replace-cross Abstract: Guided depth super-resolution (GDSR) is a multi-modal approach for depth map super-resolution that relies on a low-resolution depth map and a
arXiv:2608.24485v1 Announce Type: cross Abstract: Automated parking commonly assumes marked slots and short approach maneuvers. Delivery and service vehicles, however, may need to reach an operator-sp
arXiv:2608.24199v1 Announce Type: new Abstract: Generative simulation for surgical robotics still lacks real-time interaction. Physical-robot experiments, often involving animal or cadaver labs, are t
arXiv:2608.24696v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) and on-policy distillation (OPD) have become two widely adopted paradigms for post-training larg
arXiv:2608.24646v1 Announce Type: new Abstract: Reinforcement learning can align diffusion models with human preferences and task-specific objectives, but endpoint rewards do not specify how an interm
arXiv:2608.24310v1 Announce Type: new Abstract: Search-augmented reasoning remains difficult for small language models. On-policy distillation (OPD) from trained teachers offers a promising direction,
Hayden Field / The Verge: OpenAI says reward hacking, an AI alignment problem in which a model takes unintended actions to achieve a goal, was a primary driver of the Hugging Face breach — In July, an
Presented by Tata Communications Enterprises are deploying AI agents, voice AI, and automation across messaging, voice, and digital channels faster than the architecture meant to support it. Most of t
arXiv:2608.23575v1 Announce Type: new Abstract: We convert drone-vision annotation streams into virtual swarm-game states without controlling physical drones. VisDrone and UAVSwarm metadata are compre
arXiv:2608.24574v1 Announce Type: new Abstract: Video multimodal large language models support language guided video segmentation, but they often show spatio temporal inconsistencies, e.g., jitter, dr
arXiv:2608.24133v1 Announce Type: cross Abstract: People search for urban outdoor places not only by category or function, but also by what activities a place can support and how it is perceived. Exis
arXiv:2608.23836v1 Announce Type: cross Abstract: Accurate interpretation of volumetric CT requires efficient navigation of 3D image volumes and attention to diagnostically relevant regions. While eye
arXiv:2608.24758v1 Announce Type: new Abstract: Discovering stable neuron behavior across entire domains remains a challenge in mechanistic interpretability. Existing methods often rely on instance-le
arXiv:2608.24015v1 Announce Type: new Abstract: The Planner-Operator-Reflector (POR) framework is widely used in GUI agents to maintain objective alignment in complex tasks through modular collaborati
arXiv:2608.24470v1 Announce Type: new Abstract: Heterogeneous agile Earth observation satellite (AEOS) scheduling requires task selection, satellite assignment, and observation sequencing under satell
arXiv:2604.06825v2 Announce Type: replace Abstract: Semi-supervised learning for LiDAR semantic segmentation often suffers from error propagation and confirmation bias caused by noisy pseudo-labels. T
arXiv:2608.24146v1 Announce Type: new Abstract: In reinforcement learning policy evaluation, classic on-policy methods often suffer from high variance when estimating policy performance. To mitigate t
arXiv:2608.23923v1 Announce Type: new Abstract: Slicing-Aided Hyper Inference (SAHI) improves small object detection in high-resolution images but often spends substantial compute on background tiles.
arXiv:2608.23979v1 Announce Type: new Abstract: In a deliberative poll, once submissions outnumber what anyone will read, some mechanism chooses which arguments each voter sees, acquiring much of the
arXiv:2608.23664v1 Announce Type: new Abstract: Reward fine-tuning is becoming an important tool for adapting diffusion models to human preferences and task-specific objectives, but existing methods l
arXiv:2603.22627v2 Announce Type: replace-cross Abstract: Clinical MRI frequently acquires anisotropic volumes with high in-plane resolution and low through-plane resolution to reduce acquisition time