Knowledge catalogue
arXiv:2610.11134v1 Announce Type: new Abstract: Sparse attention reduces the cost of long-context attention, but existing kernels typically process queries independently, repeatedly loading and dequan
arXiv:2610.11183v1 Announce Type: cross Abstract: Following retrieved evidence does not guarantee factual correctness: misleading evidence can induce a model to replace an answer it previously gave co
arXiv:2610.11761v1 Announce Type: new Abstract: The genome holds the blueprint that governs the biological properties of the cell. Consequently, advancing our knowledge of genomic function is crucial
arXiv:2610.11531v1 Announce Type: new Abstract: Legged robots offer superior mobility in unstructured environments, but reliable operation in such conditions requires robust state estimation. To addre
arXiv:2610.11619v1 Announce Type: cross Abstract: We develop a model-free policy gradient method for discrete-time mean-field control (MFC). In MFC, the policy affects the objective both through the c
arXiv:2610.11146v1 Announce Type: new Abstract: Cold-start credit scoring -- deploying models with scarce labeled data, weak features, or minimal capacity -- is a recurring problem in financial machin
arXiv:2610.11475v1 Announce Type: new Abstract: Population gradient flow is a common tool for reasoning about how neural networks adapt, including after pretraining. We show that it can mispredict fin
arXiv:2610.11358v1 Announce Type: new Abstract: Cross-model KV-cache reuse remains a key challenge in modern LLM serving. Coding agents and multi-model systems increasingly route a shared context acro
arXiv:2610.12007v1 Announce Type: cross Abstract: Flow-based vision-language-action (VLA) models generate action chunks for temporally coherent robot motion, but chunked control creates a fundamental
arXiv:2609.32123v2 Announce Type: replace Abstract: Time-series diagnostic systems rarely rely on retrieving relevant historical cases, and when they do, retrieval is evaluated only indirectly through
arXiv:2610.11245v1 Announce Type: cross Abstract: KV-cache entries are stored before their future queries are known, but each decoding query needs precision in different places. We study this mismatch
arXiv:2610.10906v1 Announce Type: new Abstract: Human communities are governed by normative systems: shared standards that produce extit{norms} dictating acceptable behavior, enforced through communit
arXiv:2609.12035v3 Announce Type: replace Abstract: Cardiovascular diagnosis and treatment rest on integrating complementary modalities, such as electrocardiogram, echocardiography, and chest X-rays,
arXiv:2610.10845v1 Announce Type: cross Abstract: A large language model can only use the text that fits in its context window, and it recomputes its internal key-value (KV) state for a prompt every t
arXiv:2610.12249v1 Announce Type: cross Abstract: We study real-time motion planning in dynamic hazard fields through a controlled comparison between classical planning and learning-based methods. Rat
arXiv:2610.12343v1 Announce Type: new Abstract: Large Multi-modality Models (LMMs) have made significant progress in visual understanding and generation, but still face challenges in visual editing, p
arXiv:2610.11332v1 Announce Type: new Abstract: Structured pruning reduces the deployment cost of reasoning language models, but the resulting capability degradation can hinder subsequent on-policy di
arXiv:2610.11334v1 Announce Type: new Abstract: In LLM-based agent systems, failures can originate from early steps whose effects propagate through subsequent interactions, making their origins diffic
arXiv:2610.12090v1 Announce Type: new Abstract: Latent reasoning enables vision-language-action (VLA) models to transform multimodal observations into task-relevant internal states before generating c
arXiv:2610.11004v1 Announce Type: cross Abstract: Reconstructing spatially resolved plasma dynamics from few sensors is essential for diagnostics, reduced-order modelling and control, yet remains diff
arXiv:2610.11834v1 Announce Type: new Abstract: We study the sample complexity of noisy one-bit compressed sensing for signals drawn from a prior distribution. By characterizing the effective distribu
arXiv:2610.10623v1 Announce Type: cross Abstract: Looped Language Models (LoopLMs) offer a parameter efficient approach to scaling reasoning by reusing shared parameters across recurrent computation s
arXiv:2610.12176v1 Announce Type: new Abstract: Recursive self-improvement (RSI) of a model on non-verifiable tasks, such as open-ended research, faces a supervision bottleneck when its outputs exceed
arXiv:2610.11058v1 Announce Type: new Abstract: In autonomous driving, understanding scene topology - the connectivity between lanes and traffic elements - is critical for safe path planning and motio
arXiv:2610.11415v1 Announce Type: cross Abstract: Prediction aggregation aims to combine information from multiple predictors into a more informative one. We study this question in the setting of cali
arXiv:2610.10991v1 Announce Type: new Abstract: Image retrieval methods often rely on a single global semantic descriptor extracted from an image, e.g., the [CLS] token in vision transformers. However
arXiv:2610.12133v1 Announce Type: new Abstract: Many key-value (KV) caches are compressed before anyone knows what will be asked of them: a document cached for retrieval, a prompt prefix shared across
arXiv:2610.11876v1 Announce Type: new Abstract: Generative models can now synthesize highly realistic images, simultaneously increasing the risks of misinformation and visual forgery. Therefore, detec
arXiv:2610.11956v1 Announce Type: cross Abstract: A generated video of a task the robot is about to perform is useful guidance only if it depicts the phase the robot is actually in. We show that tempo
arXiv:2610.11287v1 Announce Type: cross Abstract: Long-horizon agents compact their history to continue within a finite context window, but a textual summary alone may not support every subsequent dec
arXiv:2610.11039v1 Announce Type: new Abstract: Active robot vision requires controlling the camera to reveal task-relevant information that is hidden from the current viewpoint. For example, determin
arXiv:2610.12185v1 Announce Type: new Abstract: Reliable robotic manipulation requires timely intervention to correct emerging deviations and restore progress after execution errors. However, recovery
arXiv:2610.12233v1 Announce Type: cross Abstract: Recursive self-improvement, the participation of AI systems in improving their own capabilities, is beginning to move from theoretical prospect to pra
arXiv:2610.11519v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) and on-policy distillation (OPD) have become two main paradigms for post-training reasoning models
arXiv:2610.12231v1 Announce Type: new Abstract: Learning from demonstration has enabled impressive robot behaviors. A common choice for policy learning is to use diffusion or flow matching (Flow-Polic
arXiv:2610.11257v1 Announce Type: new Abstract: Learned representations can lose latent degrees of freedom successively, suggesting a cascade of transitions whose underlying stability principle remain
arXiv:2610.11529v1 Announce Type: new Abstract: Self-distillation can improve reasoning without a separately trained, more capable teacher, but its effectiveness depends on how the self-teacher gains
arXiv:2610.11374v1 Announce Type: cross Abstract: CLIP serves as a foundational vision-language model and the de facto vision encoder for downstream VLMs such as LLaVA. Post-training offers a lightwei
arXiv:2602.07878v2 Announce Type: replace-cross Abstract: LLM inference is inherently expensive, even a modest slowdown can translate into substantial operating costs and severe availability risks. Re
arXiv:2610.10933v1 Announce Type: cross Abstract: Spiking language models face a tradeoff between representing continuous semantic features over short temporal windows and retaining costly nonlinear a
arXiv:2603.07233v2 Announce Type: replace Abstract: Predicting transcriptional responses to genetic perturbations is fundamental to functional genomics and therapeutic discovery. Recent deep learning
arXiv:2610.11641v1 Announce Type: new Abstract: Handcrafted minutiae detection algorithms remain fundamental to biometric science and forensic practice due to their full auditability, adherence to int
arXiv:2610.11924v1 Announce Type: new Abstract: Media-bridged time series forecasting is expanding to encompass traditional 'multivariate' and emerging 'multimodal' (e.g., through textual assistance).
arXiv:2610.11416v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as a prominent framework for complex robotic manipulation, building on the strong semantic understand
arXiv:2610.10858v1 Announce Type: cross Abstract: Analog/RF circuits remain the critical interface between digital computation and the physical world, and emerging standards from Wi-Fi 7 to 6G place s
arXiv:2610.11187v1 Announce Type: new Abstract: Single-view 3D reconstructors often produce plausible meshes that disagree with the input view, especially near depth discontinuities and self-occlusion
arXiv:2610.10947v1 Announce Type: new Abstract: Reward hacking, where a model exploits an evaluation signal without completing the intended task, threatens the reliability of deployed language model s
arXiv:2610.12333v1 Announce Type: cross Abstract: Accurate simulation of rigid-body interactions is essential for predictive physical world models. Despite recent progress in modeling object dynamics,
arXiv:2610.11164v1 Announce Type: new Abstract: We release Ride-Hailing, a large-scale ride-hailing time series dataset synthesized from DiDi's marketplace data across 200 spatial areas. Ride-Hailing
arXiv:2610.12244v1 Announce Type: new Abstract: Isolation Forest (IF) is a widely used baseline for unsupervised anomaly detection. Recent studies provide a closed-form expression for the infinite-for
arXiv:2610.11942v1 Announce Type: new Abstract: A login screen that appears after a tap on Sign in is expected; the same screen after a tap on View order is an attack. For GUI agents, safety is theref
arXiv:2610.11387v1 Announce Type: cross Abstract: Symbolic regression combines structural search with numerical fitting, but aggregate fit scores do not describe how the remaining error varies across
arXiv:2610.11370v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) grounds language models in external corpora. Agentic RAG enables iterative search, yet exposes the model to isolate
arXiv:2610.11352v1 Announce Type: new Abstract: Language models (LMs) are commonly trained with Reinforcement Learning with Verifiable Rewards (RLVR) to enhance their reasoning capabilities. However,
arXiv:2602.14032v2 Announce Type: replace Abstract: Enhancing the generalization of robotic learning in diverse unseen environments remains a fundamental challenge. Existing approaches often rely on l
arXiv:2610.11480v1 Announce Type: cross Abstract: Embodied coding agents can combine modular robot skills with frozen end-to-end policies, yet effective composition requires anticipating which policy
arXiv:2610.12424v1 Announce Type: cross Abstract: A generalist robot should not only perform diverse tasks but also improve through experience, turning what it learns during execution into capabilitie
arXiv:2610.11906v1 Announce Type: cross Abstract: We consider the problem of learning linear dynamical systems under adversarial contamination from a single trajectory of length T. While identificatio
arXiv:2610.12444v1 Announce Type: new Abstract: Quantizing AdamW's optimizer states reduces persistent storage, but quantization errors propagate through the moment recurrences and perturb subsequent
arXiv:2610.11775v1 Announce Type: new Abstract: Sparse Mixture of Experts (MoE) models scale more efficiently than dense models by routing tokens to modular expert networks that are only active for pr