Knowledge catalogue
arXiv:2602.13699v2 Announce Type: replace Abstract: Large language models (LLMs) often generate plausible yet incorrect answers, posing risks in safety-critical settings such as medicine. Human evalua
arXiv:2609.21432v1 Announce Type: new Abstract: Post-training plays a pivotal role in enhancing the reasoning capabilities and task-specific expertise of large language models (LLMs). Despite recent a
arXiv:2609.21597v1 Announce Type: new Abstract: Monocular 6-DoF pose estimation of non-cooperative targets is important for on-orbit servicing and debris removal. A single-image estimator can confuse
arXiv:2609.21363v1 Announce Type: new Abstract: Multimodal large reasoning models (MLRMs) have demonstrated remarkable capabilities in complex visual understanding. However, this very power introduces
arXiv:2609.21525v1 Announce Type: new Abstract: Preference-based reward shaping can guide reinforcement learning, but adding preference signals to the reward may unintentionally change the task being
arXiv:2609.21938v1 Announce Type: new Abstract: Transformer-based models have recently achieved strong performance on 3D reconstruction from images, and recent works extend them to process video strea
arXiv:2609.21208v1 Announce Type: new Abstract: Self-play methods that co-train a single language model as both coder and test author promise to move code-generation RL beyond fixed test suites, but t
arXiv:2512.06201v3 Announce Type: replace Abstract: We introduce K2-V2, a 360-open LLM built from scratch as a superior base for reasoning adaptation, in addition to functions such as conversation and
arXiv:2609.21229v1 Announce Type: cross Abstract: Learning robot manipulation policies typically requires substantial demonstration data, which are costly to collect on real robots. Recent methods gen
arXiv:2609.22041v1 Announce Type: new Abstract: Reinforcement learning is increasingly used to align image generators with reward signals, and Flow-GRPO recently extended this paradigm to flow-matchin
arXiv:2609.21467v1 Announce Type: new Abstract: Motion tracking can reproduce humanoid loco-manipulation from a single retargeted motion clip, but a policy trained on a fixed reference primarily repro
arXiv:2602.21583v2 Announce Type: replace Abstract: While reinforcement learning (RL) has been successfully applied to conventional quadrotors for agile and robust flight, whether actuator-level RL ca
arXiv:2609.21107v1 Announce Type: new Abstract: While learning from human motions has enabled highly dynamic humanoid skills such as dancing and martial arts in obstacle-free space, traversal through
Let’s be clear: LLMs don’t feel pain. And they don’t deserve moral standing. This new paper reports a series of experiments identifying pain-related representations in LLMs. The authors also show that
arXiv:2609.22075v1 Announce Type: new Abstract: Safe whole-body control requires coordinating collision avoidance and balance under high-dimensional, nonlinear dynamics--making safety certificates dif
arXiv:2609.21164v1 Announce Type: new Abstract: Integrating diverse data modalities --- such as clinical notes, laboratory results, and medical imaging --- is essential for advancing clinical decision
arXiv:2609.21122v1 Announce Type: new Abstract: Manipulating previously unseen objects remains challenging, as their dynamics depend on latent physical properties, such as friction and mass distributi
arXiv:2609.21365v1 Announce Type: new Abstract: Automated needle-loop hooking is a critical step in flexible microelectrode (FME) implantation. This paper presents MicroHookACT, an imitation learning-
arXiv:2609.22083v1 Announce Type: new Abstract: We present MintAct, a family of vision-language models that unifies UI grounding, multi-step navigation across mobile, desktop, and web, and visual tool
arXiv:2609.21811v1 Announce Type: new Abstract: Multimodal survival models can combine complementary prognostic information from whole-slide images and genomic profiles, but effective fusion remains c
arXiv:2609.21992v1 Announce Type: new Abstract: Most work in computational ethics treats annotator disagreement on moral content as noise to be voted away, collapsed into majority vote or the more per
arXiv:2609.21474v1 Announce Type: new Abstract: Fast-WAM shows that video-action co-training improves control without generating future video at inference, making the representation from a single vide
arXiv:2609.21316v1 Announce Type: new Abstract: Human-readable maps provide an intuitive interface for specifying robot destinations, but connecting their schematic geometry to egocentric observations
arXiv:2604.00200v2 Announce Type: replace Abstract: We study offline constrained reinforcement learning from human feedback with multiple preference oracles. Motivated by applications that trade off p
arXiv:2609.21561v1 Announce Type: cross Abstract: On-policy self-distillation provides dense, token-level supervision by conditioning a model on privileged information and distilling the resulting tea
arXiv:2609.21001v1 Announce Type: new Abstract: Substantial efforts have been devoted to making deep learning objectives, representations, and architectures interpretable, with the goal of improving t
arXiv:2609.21550v1 Announce Type: cross Abstract: Auto-bidding is central to computational advertising, where strategies must maximize advertisers' conversion value under economic constraints. It has
arXiv:2609.21659v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies solve the same manipulation task through different action interfaces, but task success alone does not establish
arXiv:2502.02542v5 Announce Type: replace Abstract: A reasoning language model (RLM) generates costly reasoning tokens, often hidden from the users, that help it excel at many tasks. Our Overthink att
arXiv:2609.21609v1 Announce Type: cross Abstract: Model-free reinforcement learning can acquire contact-rich robotic manipulation skills through trial-and-error interaction, but it often requires the
arXiv:2609.22056v1 Announce Type: cross Abstract: Multi-hop retrieval failures are not uniformly distributed across queries: they cluster in structurally predictable subpopulations. We prove two resul
arXiv:2609.21351v1 Announce Type: new Abstract: Table extraction suffers from frequent structural errors and semantic hallucinations. We propose PrismAlign, a multi-VLM framework aligning diverse visu
arXiv:2510.18082v3 Announce Type: replace Abstract: Recent advances in reinforcement learning (RL) enable its use on increasingly complex tasks, but the lack of formal safety guarantees still limits i
arXiv:2609.21753v1 Announce Type: new Abstract: Contact-rich manipulation requires policies to generate precise actions by reasoning over contact forces, robot configurations, and interaction historie
arXiv:2609.21690v1 Announce Type: new Abstract: A robot can predict failure and still be unable to prevent it. By the time a safety mechanism reacts, the nominal plan may already have spent the contro
arXiv:2603.23393v2 Announce Type: replace Abstract: Current trajectory prediction models are primarily trained in an open-loop manner, which often leads to covariate shift and compounding errors when
arXiv:2609.20831v1 Announce Type: new Abstract: We study when limiting what a language model can see improves learning. We compare standard CoT, the more general learner that reads the full trace, wit
arXiv:2305.16056v5 Announce Type: replace-cross Abstract: In this paper, we study the problem of reinforcement learning under the influence of external events. For this, we consider Markov decision pr
arXiv:2609.21470v1 Announce Type: new Abstract: Sparse representation formulates the environment perception for the end-to-end driving system as a set of discrete elements like objects and lane lines.
arXiv:2609.21448v1 Announce Type: new Abstract: This work presents extit{Robotic Multiphase Interaction (RMI)}, a setting in which liquid enters a porous material and interacts mechanically with its d
arXiv:2509.17411v2 Announce Type: replace-cross Abstract: Machine learning models optimized for average performance can perform poorly on vulnerable subpopulations. Existing approaches often rely on g
arXiv:2609.21572v1 Announce Type: new Abstract: Perceptive legged locomotion has advanced rapidly by integrating terrain geometry into learned policies, yet the integration of terrain meaning remains
arXiv:2609.21220v1 Announce Type: new Abstract: Generative robot policies can represent diverse, multimodal behaviors, but adapting pretrained policies to deployment-time constraints such as collision
arXiv:2609.21130v1 Announce Type: new Abstract: Multi-party human-robot collaboration poses a dual challenge: robot decisions should remain interpretable and auditable, while executed actions must sat
arXiv:2609.21155v1 Announce Type: new Abstract: A repair favored under an isolated input fault can be inferior when deployed modules share the faulty information. We introduce an information-interface
arXiv:2609.21145v1 Announce Type: new Abstract: The Viterbi algorithm has been previously used to perform forced alignment of audio to text to mine training data from online resources. However, many e
arXiv:2609.22085v1 Announce Type: new Abstract: Despite rapid progress, generalist robot policies remain brittle on complex, long-horizon tasks that comprise multiple stages or require repeated attemp
arXiv:2609.21515v1 Announce Type: cross Abstract: Third-party adapters for open-weight language models ship as opaque weight matrices; a recipient cannot check whether an adapter hides a backdoor with
The Information: Source: before the Hugging Face incident, OpenAI was negotiating a legally binding deal with Anthropic for the companies to stress-test each other's models — OpenAI is rethinking a ra
arXiv:2609.20899v1 Announce Type: cross Abstract: Satellite communications are an essential component of sixth-generation (6G) mobile networks, which provide ubiquitous connectivity for global service
arXiv:2511.14301v4 Announce Type: replace-cross Abstract: Transformer-based models are highly susceptible to backdoor attacks via supervised fine-tuning (SFT). To red-team existing data-poisoning defe
arXiv:2609.21211v1 Announce Type: new Abstract: Collision-free motion planning requires reliable collision models from sensed environments and validation of states along a continuous trajectory. To ma
arXiv:2609.21401v1 Announce Type: cross Abstract: Conversational AI systems produce fluent, socially appropriate responses, yet whether they participate in cooperative communication or merely simulate
The loudest voices stoking fears about AI dangers have made tremendous headway in the past two weeks. AI technology has not taken some unexpected, dangerous turn, but the hype around it — propelled by
The only true alignment seems to be between doomers, hypers and frontier lab founderes, who have converged around a misleading narrative that a. completely glosses over the important technical advance
arXiv:2609.21580v1 Announce Type: new Abstract: Fully-actuated multirotor aerial vehicles must not only track nominal wrenches but retain the 'readiness' to modulate them rapidly under disturbances. C
arXiv:2609.21621v1 Announce Type: new Abstract: Fine-grained object (FO) manipulation requires robots to distinguish a specified FO from visually similar objects and execute actions reliably despite s
arXiv:2505.04193v2 Announce Type: replace Abstract: Simplicity is a critical inductive bias for designing data-driven controllers, especially when robustness is important. Despite the impressive resul
arXiv:2609.20989v1 Announce Type: cross Abstract: As generative AI is increasingly used as a source of personal financial guidance, understanding how people appraise such advice is important for suppo
arXiv:2603.03279v2 Announce Type: replace-cross Abstract: Achieving autonomous and versatile whole-body loco-manipulation remains a central barrier to making humanoids practically useful. Yet existing