Knowledge catalogue
arXiv:2610.05854v1 Announce Type: new Abstract: Triangular attention is a core computation in AlphaFold3-style biomolecular models, with cubic cost in token count. Its shared pair bias adds a gradient
arXiv:2610.05490v1 Announce Type: new Abstract: Generative flows sample from an unnormalized target by training a flow to be balanced, and the training loss is the signal a practitioner watches. We as
arXiv:2610.05331v1 Announce Type: cross Abstract: Learning robot policies directly on physical systems remains difficult because data collection is costly and policy exploration can be unsafe. We intr
arXiv:2610.04752v1 Announce Type: cross Abstract: We study model-free online reinforcement learning (RL) for episodic tabular Markov decision processes, focusing on both gap-dependent regret and polic
arXiv:2610.06594v1 Announce Type: new Abstract: Feed-forward visual geometry transformers such as VGGT reconstruct dense 3D structure from images in a single forward pass, simplifying multi-view 3D re
arXiv:2610.05756v1 Announce Type: new Abstract: In the rapidly evolving field of construction management, worker safety remains a top priority. This paper introduces an innovative vision-based system
arXiv:2610.05637v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly trained to generate structured outputs like points and bounding boxes that downstream interfaces, agent
arXiv:2610.06400v1 Announce Type: new Abstract: Swarm robotics presents a robust and cost-effective paradigm for advanced automation in complex, dynamic environments, such as those encountered in sear
arXiv:2610.04601v1 Announce Type: new Abstract: Magnetic Resonance Imaging (MRI) is widely regarded as the optimal sensor for fetal brain analysis due to its superior soft-tissue contrast and anatomic
arXiv:2610.06317v1 Announce Type: cross Abstract: Article 50 (2) of the EU Artificial Intelligence Act requires providers of generative systems to make synthetic outputs machine-readable and detectabl
arXiv:2610.05719v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models serve as unified policies for robotic manipulation, yet their expensive inference forces robots to pause between pol
arXiv:2610.04845v1 Announce Type: new Abstract: Aligning large language models (LLMs) with human values is important for safe, efficient, and beneficial AI deployment. However, human values are multif
arXiv:2508.19131v3 Announce Type: replace-cross Abstract: The advancement of robotics and autonomous navigation systems hinges on the ability to accurately predict terrain traversability. Traditional
OpenAI initially claimed that GPT‑6 could reach artificial general intelligence (AGI). Within a month, it publicly acknowledged that current AI systems lack sufficient controllability and highlighted
arXiv:2610.03458v1 Announce Type: new Abstract: Post-training with verifiable rewards can induce reward hacking, motivating the use of monitors within the training objective rather than solely for off
arXiv:2610.03396v1 Announce Type: new Abstract: Bayesian data assimilation combines model forecasts with noisy observations, but sampling high-dimensional, non-Gaussian posteriors remains challenging.
arXiv:2610.03563v1 Announce Type: new Abstract: Sampling-based model predictive control (MPC) is a powerful approach to trajectory optimization, but its performance depends on an informative cost func
arXiv:2610.02706v1 Announce Type: new Abstract: Visuomotor policies trained via imitation learning often inherit the unnecessarily slow timing of teleoperated demonstrations. Yet uniform speedup is un
arXiv:2610.03289v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) achieve strong performance across vision-language tasks, yet the internal mechanisms by which visual and textua
arXiv:2610.03587v1 Announce Type: new Abstract: Joint embedding predictive architectures (JEPAs) predict future latent representations without reconstructing observations, enabling world models to foc
arXiv:2610.03007v1 Announce Type: cross Abstract: Long-output reasoning shifts the KV-cache bottleneck from the fixed prompt to the generated trace. Existing reasoning-cache eviction methods largely t
arXiv:2610.02274v1 Announce Type: new Abstract: Generating useful robot-training data requires more than visually plausiblescenes: objects must support interaction, placements must remain physicallyva
arXiv:2610.03196v1 Announce Type: new Abstract: A reinforcement-learning (RL) pipeline for a legged robot is assembled from proxies. A reward stands in for intended behaviour, a curriculum gate stands
arXiv:2610.03395v1 Announce Type: new Abstract: Long-horizon tasks with sparse rewards pose an exploration bottleneck for goal-conditioned reinforcement learning: a policy started from the initial sta
arXiv:2610.02853v1 Announce Type: new Abstract: Safety heads are lightweight classifiers attached to pretrained language models for flagging harmful inputs before generation. Their empirical detection
arXiv:2610.02666v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models map visual observations and language instructions to continuous robot actions, but a diffusion-based action expert (
arXiv:2610.03421v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have shown strong visual reasoning abilities, but knowledge-intensive visual question answering often requires
arXiv:2610.03240v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in public health, finance, and governance, requiring both accuracy and societal value alignment.
arXiv:2610.02364v1 Announce Type: new Abstract: Explainability is increasingly required for perception models in intelligent vehicles, yet whether explanations remain faithful under driving domain shi
arXiv:2610.02873v1 Announce Type: cross Abstract: The evolution of linguistic style in conversations is an underexplored issue in NLP. Most style-control datasets focus on sentences or assume a static
arXiv:2610.02753v1 Announce Type: cross Abstract: The practical success of conditional image generation hinges on fine-grained differences in condition alignment and visual fidelity. Classifier-free g
arXiv:2610.03127v1 Announce Type: new Abstract: Hardware-aware neural architecture search (NAS) is dominated by evaluation cost: every architecture must be trained before its reward is known. Conforma
arXiv:2610.03634v1 Announce Type: new Abstract: Terminal-using agents benefit from reinforcement learning (RL) in coding, debugging, and other multi-step terminal tasks. In these tasks, later commands
arXiv:2610.02622v1 Announce Type: new Abstract: Evaluating the occurrence and triggers of large language model (LLM) behaviors - such as sycophancy, self-preference, or over-confidence - is critical f
arXiv:2610.02460v1 Announce Type: new Abstract: Recent benchmarks rely on user simulators to evaluate AI agents in multi-turn interaction. While existing simulation techniques demonstrate surface fide
arXiv:2610.03617v1 Announce Type: new Abstract: Image-text alignment is a core problem in computer vision with applications in caption evaluation, hallucination detection, data curation, and the bench
arXiv:2610.03498v1 Announce Type: cross Abstract: Adversarial patches can disrupt Vision-Language-Action (VLA) models by manipulating visual observations, leading to failures in robot control. However
arXiv:2610.02990v1 Announce Type: new Abstract: Real-world interaction networks are inherently dynamic: edges form and dissolve as node behavior shifts over time. Most snapshot-based contrastive metho
arXiv:2610.03529v1 Announce Type: cross Abstract: Distillation has become a core primitive of large language model training, but its properties are not yet well understood. We take an entropic perspec
arXiv:2610.02844v1 Announce Type: new Abstract: Ensuring the safe and reliable deployment of large language models (LLMs) remains a fundamental challenge. Existing safety alignment approaches either i
arXiv:2606.18537v2 Announce Type: replace Abstract: Humans often acquire new skills by observing others, since observed behaviors implicitly reveal how to act reasonably in an environment. However, ob
arXiv:2610.03390v1 Announce Type: cross Abstract: Few-step neural text-to-speech models often rely on short- ened diffusion or flow-matching schedules, or on distillation from pretrained multi-step te
arXiv:2610.03543v1 Announce Type: new Abstract: Streaming video generation has benefited from distribution matching distillation (DMD), which matches the joint distribution of video frames to a video
arXiv:2610.02410v1 Announce Type: cross Abstract: Implicit neural representations (INRs) provide a flexible framework for modeling high-dimensional continuous fields, but their training is often ineff
arXiv:2610.02744v1 Announce Type: new Abstract: Epidemic intervention policies are textual artefacts that human decision-makers interpret, justify, and revise through natural language, making large la
arXiv:2610.03333v1 Announce Type: cross Abstract: Imitation learning for contact-rich manipulation requires high-quality expert data that is expensive to obtain. This makes learning a sample-efficient
arXiv:2610.02877v1 Announce Type: new Abstract: Large language models (LLMs) are widely used as automatic judges, with validity typically assessed via alignment with human scores. However, aggregate a
arXiv:2610.03374v1 Announce Type: new Abstract: Embodied world models enable scalable simulation of embodied interactions for robot learning. However, existing models are prone to Model Laziness, as t
arXiv:2610.03273v1 Announce Type: new Abstract: Reinforcement learning (RL) for learning path recommendation (LPR) faces two coupled obstacles. First, the policy must commit to a sequence of L concept
arXiv:2610.03710v1 Announce Type: cross Abstract: Inspired by human vision, we introduce a framework using active gaze to enable fine-grained bimanual manipulation with only a single stereo camera. Ey
arXiv:2610.02832v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) foundation models have scaled rapidly to enhance manipulation performance and generalizability, but this scaling incurs h
arXiv:2610.02341v1 Announce Type: new Abstract: Safe whole-body motion is essential for deploying humanoid robots in unstructured environments. Modern humanoid control commonly separates reference spe
arXiv:2610.03691v1 Announce Type: new Abstract: We present FlowHMR, a framework for recovering physically plausible global 3D human motion from monocular video. Previous learning-based methods typical
arXiv:2610.03361v1 Announce Type: cross Abstract: Critic-free reinforcement fine-tuning (RFT) for agentic large language models is often done through GRPO-style methods, which compute a group baseline
arXiv:2610.03662v1 Announce Type: new Abstract: Deploying a new decision policy creates a cold-start problem for prediction models whose targets depend on the policy's actions: historical observations
Bloomberg: Former Anthropic researcher Jacob Coxon and representatives from Anthropic, Google, OpenAI, and Meta testified at a New York City Council hearing on AI safety — Former Anthropic researcher
arXiv:2610.02910v1 Announce Type: new Abstract: Suppressing a small set of routed experts can weaken the safety behavior of a sparse Mixture-of-Experts (MoE) language model without retraining. Which e
arXiv:2609.35149v2 Announce Type: replace Abstract: Deploying, migrating, or scaling an agent can change its model, harness, infrastructure, application, and intended users. We formulate agent calibra
arXiv:2610.02828v1 Announce Type: new Abstract: Adaptive LLM reinforcement-learning post-training changes multiple training actuators online, including rollout temperature, group size, clipping, KL re
arXiv:2610.03185v1 Announce Type: new Abstract: On-policy distillation (OPD) has become an important approach to language model post-training. However, despite its performance gains, OPD can also coll