Knowledge catalogue
arXiv:2604.13079v1 Announce Type: cross Abstract: Current AI alignment paradigms rely on behavioral correction: external supervisors (e.g., RLHF) observe outputs, judge against preferences, and adjust
arXiv:2604.13705v1 Announce Type: new Abstract: Fairness in language models is typically studied as a property of a single, centrally optimized model. As large language models become increasingly agen
arXiv:2604.13824v1 Announce Type: new Abstract: World models have been emerging as critical components for assessing the consequences of actions generated by interactive agents in online planning and
arXiv:2604.13253v1 Announce Type: new Abstract: Adaptive Conformal Inference (ACI) provides distribution-free prediction intervals with asymptotic coverage guarantees for time series under distributio
arXiv:2503.06078v2 Announce Type: replace Abstract: Federated learning (FL) has emerged as a promising framework for distributed learning, enabling collaborative model training without sharing private
Can people please stop taking shots at @sama, and boycott his company instead? Violence is not the answer. This is really bad. The scary part in the US is that it doesn’t matter whether you are the CE
arXiv:2604.13409v1 Announce Type: new Abstract: In clinical practice, the robustness of deep learning models for multimodal brain tumor segmentation is severely compromised by incomplete MRI data. Thi
arXiv:2604.13804v1 Announce Type: new Abstract: The rapid evolution of multimodal large models has revolutionized the simulation of diverse characters in speech dialogue systems, enabling a novel inte
arXiv:2604.13816v1 Announce Type: new Abstract: Determining the number of clusters is a central challenge in unsupervised learning, where ground-truth labels are unavailable. The Silhouette coefficien
arXiv:2510.26491v2 Announce Type: replace Abstract: Data selection is a critical aspect of Reinforcement Learning with Verifiable Rewards (RLVR) for enhancing the reasoning capabilities of large langu
arXiv:2604.13551v1 Announce Type: new Abstract: Entity alignment (EA) aims to identify entities referring to the same real-world object across different knowledge graphs (KGs). Recent approaches based
arXiv:2604.13995v1 Announce Type: new Abstract: This paper introduces a novel approach for image and video orientation estimation by leveraging depth distribution in natural images. The proposed metho
arXiv:2604.13902v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has catalyzed significant advances in the reasoning capabilities of Large Language Models (LLMs).
arXiv:2509.21912v2 Announce Type: replace Abstract: Guidance provides a simple and effective framework for posterior sampling by steering the generation process towards the desired distribution. When
arXiv:2604.13731v1 Announce Type: new Abstract: Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents. Existin
arXiv:2602.20981v3 Announce Type: replace Abstract: Scaling multimodal alignment between video and audio is challenging, particularly due to limited data and the mismatch between text descriptions and
arXiv:2604.13491v1 Announce Type: new Abstract: With the rapid progress of Multimodal Large Language Models (MLLMs), unified MLLMs that jointly perform image understanding and generation have advanced
arXiv:2604.13598v1 Announce Type: new Abstract: Recent reinforcement learning (RL) approaches have advanced radiology report generation (RRG), yet two core limitations persist: (1) report-level reward
arXiv:2604.13410v1 Announce Type: cross Abstract: We study the problem of estimating the effect function for a continuous treatment, which maps each treatment value to a population-averaged outcome. A
arXiv:2604.13533v1 Announce Type: cross Abstract: Achieving general-purpose robotics requires empowering robots to adapt and evolve based on their environment and feedback. Traditional methods face li
arXiv:2604.13788v1 Announce Type: cross Abstract: Imitation learning (IL) policies in robotics deliver strong performance in controlled settings but remain brittle in real-world deployments: rare even
arXiv:2508.05153v2 Announce Type: replace Abstract: Category-level generalization for robotic garment manipulation, such as bimanual smoothing, remains a significant hurdle due to high dimensionality,
arXiv:2604.14035v1 Announce Type: new Abstract: Fairness in algorithmic decision-making is often defined in the predictive space, where predictive performance - used as a proxy for decision-maker (DM)
arXiv:2604.13592v1 Announce Type: new Abstract: Reasoning capabilities in large language models (LLMs) have generally advanced significantly. However, it is still challenging for existing reasoning-ba
arXiv:2604.13518v1 Announce Type: new Abstract: Self-supervised learning has emerged as a major technique for the task of learning from unlabeled data, where the current methods mostly revolve around
arXiv:2601.21667v2 Announce Type: replace-cross Abstract: Current mobile manipulation research predominantly follows an instruction-driven paradigm, where agents rely on predefined textual commands to
arXiv:2604.14142v1 Announce Type: cross Abstract: While reinforcement learning with verifiable rewards (RLVR) significantly enhances LLM reasoning by optimizing the conditional distribution P(y|x), it
arXiv:2604.13067v1 Announce Type: cross Abstract: SpeechLLMs process spoken language directly from audio, but accent and vocal identity cues can lead to biased behaviour. Current bias evaluations ofte
@GaryMarcus Essentially your prediction that LLMs to scale wouldn’t solve key fundamental problems, reasoning, factual reliability, compositionality, grounded understanding etc are now elephantine chi
Gary Marcus advocates for applying Satyagraha—a principle of nonviolent resistance emphasizing moral conviction—as a response to contemporary challenges, likely in the context of AI development and go
arXiv:2510.00573v2 Announce Type: replace Abstract: Robotic food scooping is a critical manipulation skill for food preparation and service robots. However, existing robot learning algorithms, especia
arXiv:2510.00695v3 Announce Type: replace-cross Abstract: Inherently, robotic manipulation tasks are history-dependent: leveraging past context could be beneficial. However, most existing Vision-Langu
arXiv:2509.02154v2 Announce Type: replace-cross Abstract: Variational Autoencoders (VAEs) with global priors trained under an imbalanced empirical class distribution can lead to underrepresentation of
arXiv:2604.13954v1 Announce Type: new Abstract: Existing agent-safety evaluation has focused mainly on externally induced risks. Yet agents may still enter unsafe trajectories under benign conditions.
' If a superintelligence is built, humanity will lose control over its future.' Before Canadian Senators, ControlAI's US Director Connor Leahy (@NPCollapse) explains why superintelligence could lead t
arXiv:2512.01773v2 Announce Type: replace Abstract: The rise of generalist robotic policies has created an exponential demand for large-scale training data. However, on-robot data collection is labor-
arXiv:2604.13604v1 Announce Type: cross Abstract: Binary stellar evolution simulations are computationally expensive. Stellar population synthesis relies on these detailed evolution models at a fundam
arXiv:2604.13733v1 Announce Type: new Abstract: Reinforcement learning (RL) enables high-frequency, closed-loop control for robotic manipulation, but scaling to long-horizon tasks with sparse or imper
arXiv:2604.13479v1 Announce Type: cross Abstract: Semantic segmentation of histopathology images under class imbalance is typically addressed through frequency-based loss reweighting, which implicitly
arXiv:2604.13695v1 Announce Type: new Abstract: Reliable and interpretable decision-making is essential in medical imaging, where diagnostic outcomes directly influence patient care. Despite advances
arXiv:2504.13228v4 Announce Type: replace Abstract: Mean-field game theory relies on approximating games that are intractable to model due to a very large to infinite population of players. While thes
arXiv:2506.08125v3 Announce Type: replace-cross Abstract: Large language models (LLMs) show strong reasoning abilities but often produce unnecessarily long explanations that reduce efficiency. Althoug
arXiv:2507.14005v2 Announce Type: replace Abstract: It was recently shown that dynamic programming (DP) methods for finding static CVaR-optimal policies in Markov Decision Processes (MDPs) can fail wh
Caroline O'Donovan / The San Francisco Standard: OpenAI's global policy chief, Chris Lehane, calls out AI “doomers” and says “when you put some of those thoughts and ideas out there, they do have cons
arXiv:2604.13175v1 Announce Type: new Abstract: Large language models can be aligned with human preferences through offline reinforcement learning (RL) on small labeled datasets. While single-objectiv
arXiv:2601.03027v3 Announce Type: replace Abstract: Preference alignment methods such as RLHF and Direct Preference Optimization (DPO) improve instruction following, but they can also reinforce halluc
arXiv:2604.13517v1 Announce Type: new Abstract: Temporal credit assignment in reinforcement learning has long been a central challenge. Inspired by the multi-timescale encoding of the dopamine system
arXiv:2604.04101v2 Announce Type: replace Abstract: This paper investigates the Restless Multi-Armed Bandit (RMAB) framework under individual penalty constraints to address resource allocation challen
arXiv:2508.00222v5 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Reward (RLVR) has significantly advanced the complex reasoning abilities of Large Language Models (LLMs
arXiv:2511.07717v2 Announce Type: replace-cross Abstract: Estimating robot pose from a monocular RGB image is a challenge in robotics and computer vision. Existing methods typically build networks on
arXiv:2604.13515v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) followed by Group Relative Policy Optimization (GRPO) is a common post-training recipe. We conduct a controlled ablation ov
arXiv:2604.13780v1 Announce Type: new Abstract: Soft Q-learning has emerged as a versatile model-free method for entropy-regularised reinforcement learning, optimising for returns augmented with a pen
arXiv:2603.24654v2 Announce Type: replace-cross Abstract: This article presents an argument for why quantum computers could unlock new methods for machine learning. We argue that spectral methods, in
arXiv:2510.09541v3 Announce Type: replace Abstract: Diffusion large language models (dLLMs) are emerging as an efficient alternative to autoregressive models due to their ability to decode multiple to
Supreme Court Justice Clarence Thomas on Wednesday delivered a televised broadside against progressivism, a political philosophy he described as an existential threat to America and the principles tha
arXiv:2604.13789v1 Announce Type: new Abstract: 3D Single Object Tracking (3D-SOT) aims to localize a target object across a sequence of LiDAR point clouds, given its 3D bounding box in the first fram
arXiv:2604.13082v1 Announce Type: new Abstract: Grokking in transformers trained on algorithmic tasks is characterized by a long delay between training-set fit and abrupt generalization, but the sourc
arXiv:2510.26519v3 Announce Type: replace Abstract: Existing Reinforcement Learning from Verifiable Rewards (RLVR) methods, such as Group Relative Policy Optimization (GRPO), have achieved remarkable
arXiv:2601.10245v2 Announce Type: replace-cross Abstract: Multi-step reasoning tasks like mathematical problem solving are vulnerable to cascading failures, where a single incorrect step leads to comp
arXiv:2604.14089v1 Announce Type: new Abstract: We present UMI-3D, a multimodal extension of the Universal Manipulation Interface (UMI) for robust and scalable data collection in embodied manipulation