Knowledge catalogue
arXiv:2609.35575v1 Announce Type: new Abstract: The real-world performance of current vision-language-action models is fundamentally constrained by the limited coverage of expert demonstrations and th
arXiv:2308.09456v2 Announce Type: replace Abstract: Overtaking on two-lane roads is a safety-critical decision-making problem for autonomous vehicles, since oncoming traffic may force the ego vehicle
arXiv:2609.34175v1 Announce Type: new Abstract: Vision-Language-Action (VLA) policies are typically adapted using successful demonstrations, which provide direct action supervision but rarely cover fa
arXiv:2609.31890v1 Announce Type: new Abstract: Content personalization systems in financial services must ensure fair exposure across diverse offerings-a requirement driven by contractual obligations
arXiv:2609.33248v1 Announce Type: new Abstract: Patient knowledge graphs from bedside monitoring should type their relations and state whether the data support their signs. In anesthesia and intensive
arXiv:2609.34673v1 Announce Type: new Abstract: Few-step generative models can generate high-fidelity samples within a few function evaluations. Despite this efficiency, generated samples may not exhi
arXiv:2609.32353v1 Announce Type: new Abstract: Visual token reduction is an effective way to accelerate multimodal large language models (MLLMs), but performance deteriorates rapidly under extremely
arXiv:2609.32069v1 Announce Type: new Abstract: Vision--language--action (VLA) models provide strong priors for robotic manipulation but are typically deployed as frozen policies, unable to improve fr
arXiv:2609.33973v1 Announce Type: new Abstract: Manipulating a Rubik's Cube with a single dexterous hand is a challenging test of sustained, contact-rich control: the hand must execute successive laye
arXiv:2609.34791v1 Announce Type: cross Abstract: We study finite-time concentration and convergence rates for projected two-time-scale stochastic approximation driven by a controlled Markov chain. Th
arXiv:2609.35377v1 Announce Type: new Abstract: Diffusion models trained on a finite dataset first learn to generate novel, high-quality samples and only much later collapse onto their training set. W
arXiv:2609.34009v1 Announce Type: new Abstract: Feedback-based on-policy self-distillation has emerged as a promising approach for enabling foundation models, more specifically Large Language Models (
arXiv:2609.35138v1 Announce Type: new Abstract: Latent world models predict future states for goal-directed planning using action chunks spanning multiple primitive steps. Existing methods typically u
arXiv:2609.34488v1 Announce Type: new Abstract: Looped architectures scale computation by reusing the same parameters across recurrent steps, and recent work shows that they substantially improve deep
arXiv:2609.33129v1 Announce Type: new Abstract: As the bridge between protein modality and discrete modeling, protein structure tokenization still largely relies on heavily engineered training objecti
arXiv:2609.32773v1 Announce Type: cross Abstract: Monetary-policy announcements and central-bank communications play a central role in foreign exchange markets, yet their qualitative, unstructured for
arXiv:2602.00974v2 Announce Type: replace Abstract: Label-supervised manifold alignment bridges the gap between unsupervised and correspondence-based paradigms by leveraging shared label information t
arXiv:2609.32323v1 Announce Type: new Abstract: We introduce FoundDSR, a generalizable foundation model for robust depth reconstruction across unseen data distributions using RGB-D pairs. FoundDSR beg
arXiv:2609.33086v1 Announce Type: new Abstract: Current approaches to aligning language models often make it hard to know what behavior is being rewarded or to change that reward in a targeted way. In
arXiv:2605.05660v2 Announce Type: replace Abstract: Multi-objective optimization (MOO) has received growing attention in applications that require learning under multiple criteria. However, most exist
arXiv:2609.35375v1 Announce Type: new Abstract: Scaling up robotic manipulation is primarily bottlenecked by the scarcity of real-world robot data. While recent approaches leverage human video demonst
arXiv:2609.35491v1 Announce Type: new Abstract: Few-step autoregressive video generation commonly relies on Distribution Matching Distillation (DMD), requiring a bidirectional diffusion teacher and an
arXiv:2609.34371v1 Announce Type: new Abstract: On-policy distillation (OPD) specializes pretrained video diffusion models through teacher supervision along the student's own generation trajectory. Al
arXiv:2609.34414v1 Announce Type: new Abstract: Predicting the next state is a core paradigm of World Models for modeling physical dynamics, emphasizing prediction fidelity. As World Models evolve int
arXiv:2609.35426v1 Announce Type: new Abstract: Reinforcement Learning-based post-training of Large Language Models (LLM) has been successfully applied to improve their reasoning capabilities. Existin
arXiv:2609.34207v1 Announce Type: cross Abstract: Functional data are intrinsically infinite-dimensional, and often exhibit phase variation, where corresponding events occur at different times across
arXiv:2609.33981v1 Announce Type: new Abstract: Exploration--exploitation is a central trade-off in bandit learning. While classical algorithms such as upper confidence bound methods and Thompson Samp
arXiv:2609.31715v1 Announce Type: new Abstract: Agentic recognition requires visual perception to move beyond static scene understanding and produce structured scene representations that support the p
arXiv:2609.35189v1 Announce Type: new Abstract: Post-training foundation video models on heterogeneous reward-weighted data usually assume that all data categories induce compatible updates. This assu
arXiv:2609.34233v1 Announce Type: new Abstract: Humanoid avatars extend human physical presence beyond the body, enabling people to participate in social, service, and labor activities through remotel
arXiv:2609.32596v1 Announce Type: new Abstract: Feed-forward models regress dense 3D point trajectories directly from monocular video, yet the residual after global alignment is substantial and lacks
arXiv:2609.34550v1 Announce Type: new Abstract: Vision-Language-Action (VLA) fine-tuning pairs images with actions at every step, yet typically provides only a task-level language instruction, leaving
Gary Marcus tweeted that generative AI will change the web. A reply from MMitchell (mmitchell_ai) echoes this idea and asks whether the internet’s content has deteriorated compared to four years ago,
Gentle reminder that Hugging Face was declined help from Anthropic & OpenAI models when they were being hacked by OpenAI models Self-hosted GLM 5.2 helped them protect themselves when the closed labs
arXiv:2609.32222v1 Announce Type: new Abstract: Raw 3D point clouds are a core geometric representation. Establishing their ownership is challenging because point sets are irregular, unstructured, and
arXiv:2609.32788v1 Announce Type: new Abstract: Deep learning has transformed symbolic music generation by borrowing the training paradigms of large language models, with systems such as NotaGen now p
arXiv:2609.34564v1 Announce Type: new Abstract: Post-training quantization (PTQ) efficiently compresses Vision Transformers (ViTs) without retraining, yet suffers severe accuracy degradation at low bi
GPT-6.1 Sol shows major improvements over GPT-6 Sol in our alignment evaluations, bringing it more in line with GPT-6 Astra. It’s more transparent about its limitations and more reliable at respecting
arXiv:2609.32056v1 Announce Type: new Abstract: Achieving precise control over multiple properties without sacrificing chemical validity remains a central challenge in molecular inverse design. Existi
arXiv:2609.35545v1 Announce Type: new Abstract: Epidemic policy planning often requires coordination between geographical regions, taking into account mobility-driven spillovers and how to make use of
arXiv:2609.35084v1 Announce Type: new Abstract: Group-based reinforcement learning (RL) has advanced large language models (LLMs) and is increasingly extending to agentic tasks, where sparse terminal
arXiv:2609.32064v1 Announce Type: new Abstract: This paper presents Grasp2Twist, a bimanual dexterous manipulation system that learns to grasp and twist open jar lids using reinforcement learning. Lea
arXiv:2609.32577v1 Announce Type: cross Abstract: Reinforcement learning (RL) for code agents often uses executable tests to provide binary rewards. With these rewards, Group Relative Policy Optimizat
arXiv:2609.31904v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have shown strong performance on robotic manipulation, but they often struggle to generalize to unseen tasks, conf
arXiv:2609.31924v1 Announce Type: new Abstract: Contact-rich manipulation depends on force sensing that is hard to infer from visual signals alone, both for collecting demonstrations and for training
arXiv:2609.35587v1 Announce Type: new Abstract: GPU libraries such as CUTLASS expose tens of thousands of semantically equivalent kernels for a single operation, making exhaustive autotuning expensive
arXiv:2601.13177v2 Announce Type: replace Abstract: Spinal cord stimulation (SCS) is widely used for pain management and has recently shown promise in promoting functional recovery following spinal co
Here Are My 7 Basic Prompts After 4 Years of Using ChatGPT I’ve been using ChatGPT since 2022, and over the years, through my own experiences and research, I’ve learned quite a lot about how it works.
arXiv:2609.32280v1 Announce Type: new Abstract: Hero frames are in-film stills used as source imagery for theatrical posters, streaming cover art, film database listings, and other promotional placeme
arXiv:2609.34166v1 Announce Type: new Abstract: We study the knowledge matrix of a trained feedforward network as a higher representation of its inputs. A network is a pair (W,f), a thin representatio
arXiv:2609.33637v1 Announce Type: cross Abstract: In this paper, we propose a hierarchical multi-agent reinforcement learning framework for coordinating robot teams in warehouse environments under com
arXiv:2609.33983v1 Announce Type: cross Abstract: Semantic Textual Similarity (STS) methods assume that a document's lexical content faithfully represents what it asserts. This assumption fails for di
arXiv:2609.33570v1 Announce Type: new Abstract: Group-relative policy optimization (GRPO) makes learner-side activations a major memory-computation bottleneck: gradient checkpointing reduces activatio
arXiv:2604.04204v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly embedded in educational, professional, and public infrastructure, yet widely used platforms expo
arXiv:2509.25637v2 Announce Type: replace Abstract: Preconditioning is widely used in machine learning to accelerate convergence on the empirical risk, yet its role on the expected risk remains undere
arXiv:2609.33482v1 Announce Type: new Abstract: Conformal prediction provides distribution-free finite-sample marginal coverage, but post-hoc calibration data may be too scarce to learn how uncertaint
arXiv:2609.34514v1 Announce Type: cross Abstract: As large language models (LLMs) become increasingly widespread, preventing unsafe responses to harmful prompts is essential for their safe deployment.
OpenAI’s “How we think about securing frontier RL training runs” (released September 29 2026) explains the company’s approach to safeguarding large‑scale reinforcement learning experiments. It details
arXiv:2609.34490v1 Announce Type: new Abstract: Large collections of historical Persian manuscripts have been digitized, but searching them is still slow and mostly manual. Historians usually want to
arXiv:2609.32346v1 Announce Type: new Abstract: This paper compares three human motion prediction methods - GMM-based clustering, TransFusion, and Graph-Mixer - evaluating their effectiveness in human