Knowledge catalogue
arXiv:2609.38016v1 Announce Type: new Abstract: Constrained Reinforcement Learning has recently gained increasing attention in the field of Safe Autonomous Driving, where the general mechanism is to m
Breakthroughs on every frontier. I can't wait to share more on what Praxis-1 will unlock across industries. Media Introducing Praxis-1, an open-weight World Action Model that turns our video pre-train
arXiv:2609.36505v1 Announce Type: new Abstract: Agentic reinforcement learning (ARL) with verifiable rewards improves the ability of large language models (LLMs) to tackle knowledge-intensive tasks by
arXiv:2609.37171v1 Announce Type: new Abstract: Retrieval-Augmented Generation has established itself as a fundamental framework in natural language processing, seamlessly integrating information retr
arXiv:2609.36400v1 Announce Type: cross Abstract: Deep learning classifiers for dermoscopic skin lesions often reach high in-distribution accuracy while quietly relying on spurious background cues suc
arXiv:2609.36240v1 Announce Type: new Abstract: Does representation learning stop when the training loss stops improving? We study this question for matrix Muon, whose polar-normalised updates have a
arXiv:2609.37837v1 Announce Type: new Abstract: Vision-Language Models (VLMs) remain vulnerable to cross-modal implicit risks: visual and textual inputs that appear benign in isolation can jointly eli
Intelligent data infrastructure is becoming critical as enterprises move artificial intelligence from curated pilots into production. NetApp Inc. is positioning its Novus architecture for that transit
arXiv:2609.36689v1 Announce Type: cross Abstract: Large language models have achieved significant progress in event forecasting, yet their probability outputs exhibit systematic calibration bias that
arXiv:2609.37786v1 Announce Type: new Abstract: Concept Bottleneck Models (CBMs) built on vision-language models such as CLIP represent a latent space as human-understandable concepts. These represent
arXiv:2609.36238v1 Announce Type: new Abstract: A goal that is close in space can be far away in time. Obstacles, terrain, and the agent's own capabilities determine how long it takes to get there. Ye
arXiv:2609.38136v1 Announce Type: new Abstract: Style transfer aims to render target content in the style of a reference image, but existing methods often suffer from content leakage, where objects, l
arXiv:2609.37243v1 Announce Type: cross Abstract: Cross-modal knowledge distillation transfers knowledge from a teacher modality to a student modality. Existing feature-level alignment methods typical
arXiv:2609.36935v1 Announce Type: new Abstract: Long-context reasoning is essential for complex and long-horizon tasks, yet the performance of large language models (LLMs) degrades as context length i
arXiv:2609.36239v1 Announce Type: new Abstract: Large language models (LLMs) can predict human brain activity across a variety of brain regions during natural language comprehension. Typically, howeve
arXiv:2602.20731v2 Announce Type: replace-cross Abstract: Discrete image tokenizers provide a sequential interface for vision and multimodal models, but are typically optimized for reconstruction or c
arXiv:2609.37453v1 Announce Type: new Abstract: When a user changes their mind partway through a task, an agent that has already split the task into sub-goals and paid for tool calls must decide, per
arXiv:2609.33123v2 Announce Type: replace Abstract: Self-evolving agent harnesses continually update persistent components such as memory, prompts, skills, and tools. We call this process harness evol
arXiv:2609.36364v1 Announce Type: cross Abstract: Standard video generators do not natively compact historical context into reusable memory tokens. As generation continues, the growing history makes i
arXiv:2609.36657v1 Announce Type: cross Abstract: Training models to act in accordance with an explicitly defined set of principles, or 'constitution,' has shown promise as a robust and transparent me
arXiv:2609.37456v1 Announce Type: new Abstract: Robotic ultrasound commonly targets standardized views, predefined scanning protocols, or expert-scan reproduction. We target a different role: while a
arXiv:2609.36956v1 Announce Type: cross Abstract: Manipulating next-token probabilities during generation can bypass the safety alignment of large language models. Existing approaches, however, rely o
arXiv:2609.36245v1 Announce Type: new Abstract: Latent reward models (LRMs) enable efficient alignment of video diffusion models by scoring intermediate states directly in latent space. However, we fi
arXiv:2609.37150v1 Announce Type: new Abstract: VLAs combine pretrained vision-language representations with action generation to enable language-guided control across diverse tasks, becoming a mainst
arXiv:2609.36820v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) is widely used to train reasoning language models, where it computes advantages by centering and normalizing
arXiv:2609.38172v1 Announce Type: cross Abstract: Teaching humanoids loco-manipulation skills, such as carrying diverse objects, via visual imitation is a promising path toward generalist robots. Howe
arXiv:2609.37591v1 Announce Type: cross Abstract: Test-time adaptation for vision-language navigation (TTA-VLN) enables pretrained policies to adapt online to unseen environments using only test-time
arXiv:2609.37000v1 Announce Type: cross Abstract: Cross-organizational collaboration is widely regarded as a key promise of SysML-based Model-Based Systems Engineering (MBSE), yet practitioners still
arXiv:2609.38087v1 Announce Type: new Abstract: Behavior Foundation Models (BFMs) give humanoids a promptable policy over a latent behavior space, enabling one single vector to represent a motion to i
arXiv:2609.36812v1 Announce Type: cross Abstract: Diffusion and flow policies can model complex behaviors in offline reinforcement learning (RL). However, penalizing their KL divergence from the behav
arXiv:2609.37398v1 Announce Type: new Abstract: World-Action Models (WAMs) couple action generation with predictions of how physical interactions unfold. However, current post-deployment learning para
arXiv:2609.37165v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models remain brittle under visual distribution shifts, often relying on spurious correlations tied to domain-specific fact
arXiv:2609.36940v1 Announce Type: new Abstract: Accurate dynamic scene reconstruction is important for robotic perception, where temporally consistent representations of dynamic environments are essen
arXiv:2607.17247v2 Announce Type: replace-cross Abstract: Large language model (LLM) post-training is essential for improving reasoning, adaptation, and alignment. Existing methods mainly follow two p
arXiv:2609.36520v1 Announce Type: cross Abstract: RGB-only end-to-end visual navigation policies remain vulnerable to collisions in real-world dynamic environments, motivating a dedicated safety layer
arXiv:2609.36734v1 Announce Type: new Abstract: Knowledge Distillation (KD) trains a smaller-capacity student model to imitate a larger-capacity teacher model by matching output distributions, implici
arXiv:2609.36741v1 Announce Type: new Abstract: Under irreversible resource depletion, an agent can spend resources to distinguish among latent fault models, or to change the system state so that the
arXiv:2609.36576v1 Announce Type: new Abstract: Agentic systems are now being widely used to orchestrate tools and reason over long contexts. However, the improving capabilities of the large language
arXiv:2609.38025v1 Announce Type: cross Abstract: On-policy distillation (OPD) trains a student on its own generated responses using dense, token-level supervision from a stronger teacher. Vanilla OPD
arXiv:2609.37348v1 Announce Type: new Abstract: Learning robust manipulation policies for diverse, long-horizon tasks from limited demonstrations remains a fundamental challenge in robotics. We presen
arXiv:2609.36775v1 Announce Type: new Abstract: Reinforcement Learning has significantly advanced the complex reasoning capabilities of MLLMs. However, prevailing RL algorithms suffer a severe failure
arXiv:2609.36944v1 Announce Type: new Abstract: Group-relative policy optimization relies on reward-derived advantages and sequence-level likelihood weights, both of which can be sensitive to localize
arXiv:2609.36116v1 Announce Type: new Abstract: We study how to build more capable general-purpose agents by extending large language models (LLMs) with native typed decision-making. We introduce Dyad
arXiv:2502.04492v3 Announce Type: replace Abstract: The advancement of LLMs and their accessibility have triggered renewed interest in multi-agent reinforcement learning as robust and adaptive framewo
arXiv:2609.36802v1 Announce Type: new Abstract: A key strength of Proximal Policy Optimization (PPO) is its learned critic, which uses historical trajectories collected during reinforcement learning t
arXiv:2609.36740v1 Announce Type: new Abstract: Many recommender systems such as for e-commerce and news platforms aim to provide users with rankings they are likely to interact with. Off-Policy Learn
arXiv:2609.38046v1 Announce Type: new Abstract: Egocentric human demonstrations offer an accessible source of task experience, but differences in body scale and controller response, together with miss
arXiv:2609.37181v1 Announce Type: cross Abstract: Human demonstrations capture diverse scenes and rich whole-body skills without requiring robot teleoperation. Prior work on egocentric transfer has em
arXiv:2609.36803v1 Announce Type: new Abstract: Real-time video understanding requires incrementally maintaining a memory of streaming content, and optimizing this requires dense process signals. On-P
arXiv:2609.36460v1 Announce Type: cross Abstract: Several tonal pitch spaces and computational models have been proposed to analyze tonal structure in Western tonal music, many of them grounded in pri
arXiv:2609.37359v1 Announce Type: cross Abstract: Coding agents can now write, run, and debug programs with little human help. Robot tasks, however, are usually specified by a sentence that leaves out
arXiv:2609.37162v1 Announce Type: new Abstract: RGB-T object tracking leverages the complementary characteristics of visible and thermal infrared modalities to improve robustness under adverse conditi
arXiv:2609.35807v1 Announce Type: cross Abstract: LLM agents can make unsafe tool calls even when instructed to behave safely. Existing defenses constrain agents before execution, modify tool inputs/o
arXiv:2609.36952v1 Announce Type: cross Abstract: Large language models (LLMs) excel at token-level generation but may learn undesirable abstract semantics and lack comprehensive perception. LLM-JEPA
arXiv:2602.11328v2 Announce Type: replace Abstract: As people turn to LLMs for social advice, understanding their behavior in such contexts becomes essential. In this work, we focus on behavioral disp
arXiv:2609.37501v1 Announce Type: cross Abstract: We propose RegLLM, a diagnostic harness for bounded autonomy in regulated agentic workflows. It instruments six trustworthiness signals: citation vali
arXiv:2512.17323v2 Announce Type: replace Abstract: Event-based scene synthesis reconstructs target RGB frames from sparse image observations and asynchronous event streams, encompassing both video fr
arXiv:2609.36578v1 Announce Type: cross Abstract: Scheduling problems arise from repeatedly selecting one item from a set of candidates based on their states. These problems often reduce to assigning
arXiv:2609.36174v1 Announce Type: new Abstract: We consider fair resource allocation in sequential decision-making environments modeled as major-minor weakly coupled Markov decision processes (M2WCMDP
arXiv:2609.36671v1 Announce Type: new Abstract: While the 'Matthew Effect' and filter bubbles are widely recognized outcome-level biases in recommender systems, we reveal that Diffusion Recommender Mo