Knowledge catalogue
arXiv:2512.15493v2 Announce Type: replace Abstract: Physical systems are naturally parameterized in terms of geometric entities and their transformations. While exact equivariance can be a powerful in
arXiv:2511.09484v3 Announce Type: replace-cross Abstract: Learning agile robotic policies requires large-scale demonstrations, but translating abundant human motion data to robots is bottlenecked by t
arXiv:2609.35268v1 Announce Type: new Abstract: Reinforcement learning (RL) with sparse rewards is challenging because delayed outcomes provide little guidance about which intermediate computations ca
arXiv:2606.15197v3 Announce Type: replace Abstract: Optimization modeling is inherently hierarchical, requiring a precise sequence of symbolic commitments. Traditional learning-based automated optimiz
arXiv:2609.34756v1 Announce Type: cross Abstract: Adapting pretrained models to downstream tasks with limited data has become a central paradigm in modern deep learning. Yet, despite its widespread pr
arXiv:2609.34695v1 Announce Type: new Abstract: Reward shaping is fundamental to modern robotic control with deep reinforcement learning (RL), yet practitioners still rely heavily on heuristic princip
arXiv:2609.33781v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) enhances reasoning in large language models (LLMs) through outcome-level feedback, yet recent appr
arXiv:2605.06140v2 Announce Type: replace Abstract: Generative modeling of physical systems, such as molecules, requires learning distributions that are invariant under global symmetries, such as rota
arXiv:2603.09084v2 Announce Type: replace Abstract: Lip synchronization refers to the task of modifying facial lip movements such that they are temporally aligned with a given audio signal. It is a fu
arXiv:2609.34006v1 Announce Type: new Abstract: Contact-rich policies often fail because distinct physical states look alike yet require different actions. Cameras may not reveal whether a connector i
arXiv:2609.33200v1 Announce Type: new Abstract: On-policy self-distillation trains reasoning models on their own trajectories using dense token distribution guidance from a privileged teacher with acc
arXiv:2609.35319v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own trajectories with dense teacher supervision. Recent work on OPD for multi-turn autonomous agent
arXiv:2609.34319v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models enable generalizable robotic control but remain computationally expensive. Token caching provides a training-free, p
arXiv:2609.34106v1 Announce Type: new Abstract: Large visual foundation models have demonstrated remarkable transferability across a wide range of downstream tasks. To deploy such models efficiently,
arXiv:2609.34074v1 Announce Type: cross Abstract: In school choice, a lottery number is often used by the matching mechanism to break ties when there are more students who prefer the same school than
arXiv:2609.34590v1 Announce Type: cross Abstract: Language models often process long inputs sequentially in chunks, but continuing to read after sufficient evidence has been acquired wastes computatio
arXiv:2509.19453v2 Announce Type: replace-cross Abstract: We investigate when foundation models converge towards shared representations, and how this convergence depends on model capacity, training re
arXiv:2609.33291v1 Announce Type: cross Abstract: Many generative systems return multiple candidate responses and are evaluated according to the best one. Recent work shows that, when demonstrations a
arXiv:2609.32591v1 Announce Type: cross Abstract: Data-driven model predictive control (MPC) combines learned world models with online trajectory optimization, achieving strong performance in continuo
arXiv:2609.35058v1 Announce Type: new Abstract: Effective multi-turn agents require interaction strategies that coordinate information gathering, actions, and feedback over long horizons. GRPO is a re
arXiv:2609.33157v1 Announce Type: new Abstract: DAgger improves robot policies by aggregating expert supervision from states visited during policy execution. Robot-gated DAgger automates expert querie
arXiv:2609.32665v1 Announce Type: cross Abstract: ELBO-based reinforcement learning offers a sampler-agnostic approach to fine-tuning flow matching models with reward feedback. Timestep weighting in E
arXiv:2609.35760v1 Announce Type: new Abstract: When a large language model (LLM) agent executes the same task, token consumption can vary by over an order of magnitude across runs. The agent chooses
arXiv:2609.33125v1 Announce Type: new Abstract: Co-training offers a straightforward way to build a multi-task vision-language-action (VLA) policy, but can fall short of the performance achieved by tr
arXiv:2609.32849v1 Announce Type: new Abstract: Learning transferable representations for dynamic text-attributed graphs (DyTAGs) requires models to capture underlying interaction dynamics that persis
The US executive branch is no longer acknowledging the existence of 'artificial intelligence.' Going forward, official policy websites, policy documents, and press releases will refer only to 'Super I
arXiv:2609.34539v1 Announce Type: new Abstract: Diffusion Transformers (DiTs) have emerged as the dominant architecture for high-fidelity image and video generation. Recent DiT systems increasingly us
arXiv:2609.33414v1 Announce Type: new Abstract: Test-time reinforcement learning enables vision-language models (VLMs) to adapt using unlabeled inputs. However, repeated sampling under fixed visual co
arXiv:2609.35609v1 Announce Type: new Abstract: Constrained decoding for Masked Diffusion Language Models (MDLMs) aims to ensure that generated outputs satisfy a specified structure or syntax constrai
arXiv:2605.05389v2 Announce Type: replace Abstract: Most neural methods for Vehicle Routing Problems (VRPs) are limited to Euclidean settings or simple graphs. In this work, we instead consider multig
arXiv:2609.34667v1 Announce Type: cross Abstract: Fine-tuning pre-trained models on specialized tasks with scarce data is central to modern deep learning. Despite its empirical success, theoretical un
arXiv:2609.34447v1 Announce Type: cross Abstract: On-policy distillation (OPD) is becoming an important component of large language model (LLM) post-training for transferring the reasoning capability
arXiv:2609.32169v1 Announce Type: cross Abstract: Nonlinear dynamical systems with memory arise across science and engineering, yet uncertainty quantification for efficient forecasting methods such as
arXiv:2609.34223v1 Announce Type: new Abstract: This work aims to improve how audio-visual large language models (AVLLMs) associate speech with the correct visible speaker in multi-speaker scenes. We
arXiv:2601.06597v3 Announce Type: replace Abstract: Can we design a model such that its stochastic training favours a desired class of solutions without enforcing an explicit penalty? Under suitable c
arXiv:2609.34458v1 Announce Type: cross Abstract: Classical statistical theory is insufficient to explain the successes of general-purpose AI models, because it depends on handcrafted inductive biases
arXiv:2609.32831v1 Announce Type: new Abstract: Unified multimodal models combine understanding, generation, and editing within a single network, offering a promising foundation for versatile multimod
arXiv:2609.34688v1 Announce Type: new Abstract: Reward-maximizing reinforcement learning (RL) is widely used to post-train stochastic diffusion and flow policies for text-to-image (T2I) generation. Ho
arXiv:2609.34036v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own rollouts using dense supervision from a teacher. In multi-turn environments, a mistake at a cri
arXiv:2609.33888v1 Announce Type: new Abstract: Can vanilla policy optimization explore enough to achieve near-optimal regret in stochastic contextual bandits? We show that standard exponential policy
arXiv:2609.35020v1 Announce Type: new Abstract: Vision Sparse Autoencoders (SAEs) have become a popular tool in Mechanistic Interpretability due to their presumed ability to disentangle complex featur
arXiv:2607.11397v2 Announce Type: replace Abstract: Human videos provide rich information about object manipulation at a scale difficult to reproduce with robots, but often lack action annotations tha
arXiv:2609.34250v1 Announce Type: new Abstract: Pretrained world action models (WAMs) provide generalist capabilities across diverse robotic manipulation tasks, yet improving target-task performance t
arXiv:2602.14143v2 Announce Type: replace Abstract: When a model solves a problem on one attempt and fails it on the next, what separates the two is rarely the final answer token; it is the trajectory
arXiv:2511.00071v2 Announce Type: replace Abstract: Parity is exactly determined by the least significant bit (LSB), so machine learning is unnecessary for solving the task. This work instead uses par
arXiv:2609.33740v1 Announce Type: cross Abstract: Estimating causal effects with continuous treatments in observational studies is challenging due to confounding, model misspecification, and high-dime
arXiv:2609.32532v1 Announce Type: new Abstract: A generalization gap in reinforcement learning (return on training levels minus return on held-out levels) is usually reported without a reference point
arXiv:2609.32002v1 Announce Type: cross Abstract: The rank r in LoRA is widely treated as a capacity control: a smaller rank is assumed to yield a simpler model that generalizes better. We show that,
arXiv:2609.35583v1 Announce Type: new Abstract: Robustness evaluation must examine diverse visual perturbations, while benchmarks cover only some real-world conditions and physical testing is costly.
arXiv:2609.32452v1 Announce Type: cross Abstract: Reflective prompt optimization revises instructions using examples of a model's behavior, but which evidence the reflector should receive remains uncl
arXiv:2609.34732v1 Announce Type: new Abstract: Representation alignment speeds up diffusion transformer training by pulling an intermediate block of the model (student) toward features of a frozen pr
arXiv:2609.32677v1 Announce Type: cross Abstract: Self-improving agents increasingly rely on proxy verifiers to choose policy updates, yet deployment can change the world in which those updates are ev
arXiv:2504.12860v2 Announce Type: replace-cross Abstract: We study the effectiveness of randomizing split-directions in random forests. Prior literature has shown that, randomization can reduce varian
arXiv:2609.32488v1 Announce Type: cross Abstract: Dense retrieval powers retrieval-augmented generation, semantic search, and question answering, yet the theoretical basis for choosing between shared
arXiv:2609.32301v1 Announce Type: new Abstract: Active feature acquisition (AFA) sequentially selects informative features under budget constraints. However, existing policies rarely distinguish wheth
arXiv:2609.32489v1 Announce Type: cross Abstract: In tri-modal visual question answering (VQA), auxiliary text is commonly used to complement visual and textual inputs, yet its reliability is often un
arXiv:2609.34012v1 Announce Type: new Abstract: Neural PDE surrogates increasingly incorporate structural priors, yet it is often unclear whether their gains arise from physics-specific information or
arXiv:2609.33668v1 Announce Type: new Abstract: Pseudo-labeling has become a cornerstone of learning from unlabeled data in semantic segmentation. Yet its effectiveness drops sharply in real-world sce
arXiv:2609.32083v1 Announce Type: new Abstract: Deploying AI systems requires deciding when to delegate tasks and when humans should intervene to monitor and mitigate risk induced by AI operations. Th
arXiv:2609.34849v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards provides a sparse post-training signal: a single binary outcome evaluates the entire rollout, and every t