Knowledge catalogue
arXiv:2606.02198v1 Announce Type: new Abstract: Prediction tasks over individual futures, which are inherently noisy, often admit multiple similarly accurate models. When these models produce differen
arXiv:2606.00844v1 Announce Type: cross Abstract: Bounding-box regression is a fundamental component of object detection, playing a critical role in precise object localization. Existing Intersection-
Gary Marcus argues that SpaceX's valuation is significantly inflated, contending that the company is not worth the trillion-dollar valuations that have been suggested. The critique appears to challeng
arXiv:2606.00708v1 Announce Type: new Abstract: Automated data science is a structured model-selection problem. A solution must choose data transformations, feature representations, architecture, trai
arXiv:2606.02352v1 Announce Type: new Abstract: Robust self-supervised learning of multi-modal video representations is critical for real-world applications such as driver distraction detection, where
arXiv:2606.00399v1 Announce Type: new Abstract: Machine unlearning aims to remove the influence of specific training samples while preserving the model's utility. Existing single-objective approaches,
arXiv:2601.18783v2 Announce Type: replace-cross Abstract: Balancing safety, efficiency, and operational costs in highway driving poses a challenging decision-making problem for heavy-duty vehicles. A
arXiv:2606.01483v1 Announce Type: cross Abstract: Long-form automatic speech recognition (ASR) requires both high accuracy and low latency, but existing systems force a trade-off between the two. Chun
arXiv:2606.01084v1 Announce Type: cross Abstract: Combinatorial routing problems such as the Traveling Salesman Problem (TSP) and the Capacitated Vehicle Routing Problem (CVRP) are fundamental NP-hard
arXiv:2606.00174v1 Announce Type: cross Abstract: Electromyography (EMG) directly reflects muscle activation and is a key sensing modality for gesture recognition, prosthetic control, and wearable int
arXiv:2606.02432v1 Announce Type: new Abstract: Task-oriented dexterous grasp generation aims to produce dexterous grasp poses that are both physically plausible and functionally suitable for specifie
arXiv:2606.02107v1 Announce Type: cross Abstract: This paper proposes a Network Distributed Multi-Agent Reinforcement Learning (ND-MARL) framework for quadcopter consensus control. Compared to convent
NEW: Ahead of the SpaceX IPO, we tracked hundreds of promises that Musk has made over the years (FSD, Mars etc). His success rate is…not good. And it’s getting worse. Some actual data in our months lo
arXiv:2602.01460v3 Announce Type: replace-cross Abstract: Policy-gradient methods are widely used in reinforcement learning, yet training often becomes unstable or slows down as learning progresses. W
arXiv:2511.20409v2 Announce Type: replace Abstract: Text normalization methods such as stemming and lemmatization are fundamental components of NLP pipelines. As new normalization tools are developed
Not convinced that this kind of nationalization by fiat is at all the right way to go (and for that matter don’t expect the current breed of technology to generate trillions), but I am glad that Sande
arXiv:2602.01753v3 Announce Type: replace Abstract: Aligning objects with corresponding textual descriptions is a fundamental challenge and a realistic requirement in vision-language understanding. Wh
arXiv:2509.03456v2 Announce Type: replace-cross Abstract: Off-policy evaluation (OPE) and off-policy learning (OPL) are foundational for decision-making in offline contextual bandits. Recent advances
arXiv:2606.00135v1 Announce Type: cross Abstract: Tool-calling is a central component of modern large language model (LLM) agents, equipping them with skills beyond their parametric knowledge. This pa
arXiv:2606.00467v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used for zero-shot annotation and LLM-as-a-judge tasks, yet their reliability hinges on how model-intern
arXiv:2603.03291v2 Announce Type: replace-cross Abstract: Reward Models (RMs) are crucial for online alignment of language models (LMs) with human preferences. However, RM-based preference-tuning is v
arXiv:2606.01039v1 Announce Type: cross Abstract: On-policy distillation (OPD) is a widely used technique to transfer capabilities from capable teacher language models to the base student models, and
OpenAI: OpenAI says it has not donated to any super PACs and does not have an employee-funded PAC, and that Greg Brockman's support for Leading the Future is personal — AI is going to be one of the mo
arXiv:2602.05395v2 Announce Type: replace-cross Abstract: A simple strategy for improving LLM accuracy, especially in math and reasoning problems, is to sample multiple responses and submit the answer
arXiv:2511.05650v2 Announce Type: replace-cross Abstract: Alignment has greatly improved large language models (LLMs)' output quality at the cost of diversity, yielding highly similar outputs across g
arXiv:2606.00990v1 Announce Type: new Abstract: A mobile robot following a graph of known routes can make costly navigation errors when a temporary obstacle blocks a critical edge: waiting too long be
arXiv:2606.00537v1 Announce Type: new Abstract: Recent vision-language-action and diffusion-based robot policies often use action chunking, where each policy query predicts a sequence of future action
arXiv:2601.04539v2 Announce Type: replace-cross Abstract: In recurrent neural networks (RNNs) used to model biological neural networks, noise is typically introduced during training to emulate biologi
arXiv:2606.00826v1 Announce Type: new Abstract: Strategic machine learning investigates scenarios where agents manipulate their features to receive favorable decisions from predictive models. To addre
arXiv:2606.01636v1 Announce Type: new Abstract: Post-training via Group Relative Policy Optimization (GRPO) has emerged as a powerful paradigm for aligning flow-based generative models with human pref
arXiv:2604.14514v2 Announce Type: replace Abstract: Healthcare disparities persist across socioeconomic boundaries, often attributed to unequal access to screening, diagnostics, and therapeutics. Howe
arXiv:2404.01356v3 Announce Type: replace-cross Abstract: Deep neural networks are vulnerable to adversarial perturbations that can simultaneously degrade prediction robustness and individual fairness
arXiv:2606.01851v1 Announce Type: new Abstract: Learning a good action embedding space is fundamental to scalable robot policy learning, yet existing methods treat action latents as task-specific inte
arXiv:2606.01649v1 Announce Type: new Abstract: Generating physically consistent 3D tabletop scenes is a fundamental yet underexplored problem for interactive and generalist robotic learning. The chal
arXiv:2606.01894v1 Announce Type: new Abstract: Accurate Remaining Useful Life prediction is critical for industrial predictive maintenance. However, real-world deployment is challenging due to the ir
arXiv:2606.02388v1 Announce Type: cross Abstract: Reinforcement learning (RL) improves large language model (LLM) agents by teaching them which actions lead to high rewards, but provides little superv
arXiv:2606.02565v1 Announce Type: new Abstract: Ultra-high-resolution image sensors offer the potential to capture fine spatial details critical for many visual perception tasks, but acquiring and pro
arXiv:2606.01920v1 Announce Type: new Abstract: Diffusion-based dataset distillation has recently emerged as a promising paradigm for condensing large-scale datasets into compact synthetic sets. By le
arXiv:2508.08337v3 Announce Type: replace-cross Abstract: Algorithmic fairness research has largely framed unfairness as discrimination along sensitive attributes. However, this approach limits visibi
arXiv:2606.01036v1 Announce Type: new Abstract: This position paper argues that to obtain reliable embodied reward models, the community must invest in ``bad'' robot data: failed, suboptimal, error-pr
arXiv:2602.19789v2 Announce Type: replace Abstract: This position paper argues that the machine learning community must move from preaching to practising data frugality for responsible artificial inte
arXiv:2606.01722v1 Announce Type: cross Abstract: For decades, distributed systems have typically assumed that correct participants execute protocol-specified behavior with stable, externally defined,
arXiv:2606.00395v1 Announce Type: cross Abstract: Mixture of Experts (MoE) Large Language Models (LLMs) achieve strong performance at scale. However, reinforcement learning (RL) on MoE-based LLMs ofte
arXiv:2602.07298v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) represent a promising frontier for recommender systems, yet their development has been impeded by the absence of
arXiv:2602.02098v2 Announce Type: replace-cross Abstract: Multi-task reinforcement learning trains generalist policies that can execute multiple tasks. While recent years have seen significant progres
arXiv:2606.00970v1 Announce Type: new Abstract: We study risk-neutral control in Markov decision processes with an absorbing catastrophic state. Even though rewards are linear and the agent has no uti
arXiv:2606.00369v1 Announce Type: cross Abstract: Safe global deployment of AI models requires alignment with human values that vary across cultures. Yet rater pools in safety evaluation datasets rema
arXiv:2606.02301v1 Announce Type: cross Abstract: Chronic pain diminishes quality of life by decreasing functional ability, yet objectively measuring this functional impact remains challenging in real
arXiv:2606.00757v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) suffer from overfitting and over-squashing of long-range information. Stochastic graph augmentations (e.g., edge deletion)
arXiv:2606.00147v1 Announce Type: cross Abstract: Domain-specific supervised fine-tuning (SFT) often improves in-domain performance at the cost of degrading a model's general capabilities. We view thi
arXiv:2602.06806v2 Announce Type: replace Abstract: Text-to-image diffusion models achieve impressive generation quality but inherit and amplify training-data biases, skewing coverage of semantic attr
arXiv:2411.15076v3 Announce Type: replace-cross Abstract: Spatial transcriptomics (ST) provides essential spatial context by mapping gene expression within tissue, enabling detailed study of cellular
arXiv:2602.14065v2 Announce Type: replace Abstract: Knowledge-intensive Visual Question Answering (KI-VQA) frequently suffers from severe knowledge conflicts caused by the inherent limitations of open
arXiv:2604.01802v2 Announce Type: replace Abstract: Real-time inference of inaccessible interior physical fields from sparse boundary observations is a fundamental but unresolved problem in scientific
arXiv:2510.01800v3 Announce Type: replace Abstract: Academic regulation advising is essential for helping students interpret and comply with institutional policies, yet building effective systems requ
arXiv:2601.22947v2 Announce Type: replace Abstract: Masked diffusion language models (MDLMs) generate text by unmasking tokens in parallel and have recently emerged as alternatives to autoregressive l
arXiv:2506.11083v3 Announce Type: replace Abstract: We introduce RedDebate, a novel multi-agent debate framework that provides the foundation for Large Language Models (LLMs) to identify and mitigate
arXiv:2606.00263v1 Announce Type: cross Abstract: This letter studies CSI denoising for MIMO--OFDM with variable NR resource block (RB) allocations. ReFLEX is a length-generalizable Transformer whose
arXiv:2606.00143v1 Announce Type: cross Abstract: Financial markets are inherently non-stationary, exhibiting frequent regime shifts and structural changes that render traditional Portfolio Management
arXiv:2606.00680v1 Announce Type: new Abstract: Offline reinforcement learning (RL) aims to optimize policies from pre-collected datasets. A bottleneck of this paradigm is managing epistemic uncertain