Knowledge catalogue
arXiv:2610.11012v1 Announce Type: new Abstract: Powerful misaligned AI models might recognize alignment evaluations and strategically behave well on them, rendering direct audits uninformative. Howeve
arXiv:2610.11380v1 Announce Type: new Abstract: Diffusion models have achieved remarkable success in generative modeling, with their sampling procedures routinely modified to control generation and im
arXiv:2610.11023v1 Announce Type: new Abstract: Identity-preserving video generation aims to maintain a subject's identity while synthesizing realistic videos. Yet a single reference portrait captures
arXiv:2610.10552v1 Announce Type: cross Abstract: Comparing parameter-efficient fine-tuning recipes under a single, shared learning rate is a common but flawed practice: when the arms being compared h
arXiv:2610.12230v1 Announce Type: cross Abstract: Text prompting is an indirect interface for poster generation, requiring users to encode inherently two-dimensional composition intent into a one-dime
arXiv:2610.10945v1 Announce Type: new Abstract: We present GHARP (Real-time Gaussian Head Animation from Large-scale Reconstruction Prior), a method that animates 3D human heads in real time from a fe
arXiv:2610.12401v1 Announce Type: new Abstract: Kilometer-scale regional weather forecasting is essential for local weather warnings and weather-sensitive decisions. Existing data-driven approaches of
arXiv:2512.00911v2 Announce Type: replace Abstract: Panoramic cameras provide a 360{eg} field of view and are widely used in panoramic vision, immersive visual computing, and robotic perception. Howev
arXiv:2610.11019v1 Announce Type: cross Abstract: Multimodal large language models learn mostly from paired image-text data or annotated video, and raw web video is rarely used to further train an exi
arXiv:2610.11959v1 Announce Type: new Abstract: Reinforcement learning (RL) is the central training paradigm for advancing large foundation models towards self-improvement. This report introduces the
arXiv:2610.12194v1 Announce Type: new Abstract: World modeling has emerged as an effective co-training objective for robot policies, giving rise to World Action Models (WAMs) that jointly predict acti
arXiv:2610.11442v1 Announce Type: new Abstract: Human mobility generation, an important task in urban research, synthesizes trajectory data for urban planning and transportation management. Human mobi
arXiv:2610.11605v1 Announce Type: cross Abstract: We introduce NanoProof, to our knowledge the first factorized execution-guided theorem prover in Lean 4 whose training data, extraction tooling, train
arXiv:2601.14994v2 Announce Type: replace-cross Abstract: Data contamination can invalidate benchmark evaluation when a model benefits from memorized evaluation content rather than genuine generalizat
arXiv:2610.10975v1 Announce Type: cross Abstract: Muon has motivated a growing family of optimizers that compose multiple matrix normalizations, but these methods remain fragmented and lack a unified
arXiv:2606.17924v2 Announce Type: replace-cross Abstract: Current Vision-Language-Action (VLA) models face a trade-off between efficient action generation and explicit deliberation. Directly decoding
arXiv:2610.11646v1 Announce Type: new Abstract: German is a morphologically rich language whose syllable structure is exceptionally well-predicted by the Knuth--Liang hyphenation algorithm. We ask whe
arXiv:2610.12285v1 Announce Type: new Abstract: Learning to predict how the world evolves can provide vision-language-action (VLA) policies with predictive context for long-horizon control, but its ef
arXiv:2610.12010v1 Announce Type: new Abstract: Predictive representation learning from photoplethysmography (PPG) can violate causal information access even with causal attention, as normalization, n
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:2610.11374v1 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: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:2610.12444v1 Announce Type: new Abstract: Quantizing AdamW's optimizer states reduces persistent storage, but quantization errors propagate through the moment recurrences and perturb subsequent
arXiv:2610.12469v1 Announce Type: new Abstract: Instruction-guided image editors have become highly capable, yet improving them further still depends on human-edited training pairs or external reward
arXiv:2603.08260v2 Announce Type: replace Abstract: Existing data generation methods for robot learning suffer from limited exploration, embodiment gaps, low signal-to-noise ratios, and domain shifts,
arXiv:2610.11825v1 Announce Type: new Abstract: Detecting intra-operative speech impairment during awake craniotomy is essential for preserving language function. However, automated detection remains
arXiv:2610.11361v1 Announce Type: cross Abstract: A 4D audio-visual scene comprises a video, the dynamic geometry it depicts, and the sound sources that populate it, each with its own position and tra
arXiv:2610.11132v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) equips large language models (LLMs) with specialized capabilities, but often comes at the cost of forgetting the general
arXiv:2610.10850v1 Announce Type: new Abstract: As AI models move toward clinical decision-making and personalized treatment, understanding what a model learns is important beyond predictive accuracy
arXiv:2610.11650v1 Announce Type: cross Abstract: Similar agent skills can share instructions but differ in their conditions of use. Query-based text selection may retain shared instructions and omit
arXiv:2610.12282v1 Announce Type: new Abstract: Streaming 3D reconstruction must preserve evidence from each frame while processing an expanding scene online. Spatial memory is a natural fit because i
arXiv:2610.10571v1 Announce Type: new Abstract: Electroencephalography (EEG) provides a non-invasive measure of ongoing neural activity, but building general-purpose EEG models remains challenging due
arXiv:2610.11746v1 Announce Type: new Abstract: Real-time video super-resolution requires high spatio-temporal fidelity under strict latency constraints, challenging diffusion models due to their iter
arXiv:2610.12126v1 Announce Type: cross Abstract: General-purpose service robots need navigation systems that can handle diverse human requests in unfamiliar environments, combining task generality wi
arXiv:2610.11216v1 Announce Type: cross Abstract: Diffusion and autoregression (AR) have long been seen as different categories of generative models, with diffusion specialising in continuous fields a
arXiv:2610.10972v1 Announce Type: new Abstract: Assessing useful reuse in neural PDE solvers is challenging: final accuracy can reflect source learning and target-time computation. Our reuse contract
arXiv:2610.12099v1 Announce Type: new Abstract: World action models (WAMs) aim to answer a coupled physical question: given a task instruction, what motion should the robot execute, and how will that
arXiv:2610.11322v1 Announce Type: new Abstract: Geometrically faithful and functional articulated 3D assets are essential for real-to-sim robot manipulation, where policies trained in simulation must
arXiv:2610.12451v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have emerged as powerful foundations for robotic manipulation, but their reliance on fixed camera configurations dur
arXiv:2610.12435v1 Announce Type: cross Abstract: Teaching a humanoid to follow instructions with its whole body runs into two obstacles. Its action space is large and tightly coupled: legs, arms, and
arXiv:2610.10761v1 Announce Type: cross Abstract: Linear attention is a tractable model for understanding the mechanisms governing in-context learning in transformers. For linear regression tasks, rec
arXiv:2610.11520v1 Announce Type: new Abstract: End-to-end speech parsing, a task recently proposed, consists in predicting both the transcription and the syntactic tree for a spoken utterance. Existi
arXiv:2610.11620v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) enables large language models (LLMs) to adapt to specialized tasks, but often at the cost of degrading general ca
arXiv:2610.12382v1 Announce Type: new Abstract: Faithful visual world simulation requires generated videos to maintain 4D world consistency, encompassing both static and dynamic consistency. Static co
arXiv:2605.25077v2 Announce Type: replace Abstract: Recent video world models enable interactive camera navigation but provide limited control over individual objects. We study persistent object-state
arXiv:2610.12459v1 Announce Type: new Abstract: Video generators and video-based world models can synthesize plausible visual trajectories, but long-horizon procedural tasks require generation to adap
arXiv:2610.12417v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) struggle with spatial, embodied, physical, and temporal reasoning. We hypothesize that these failures reflect
arXiv:2610.09003v1 Announce Type: new Abstract: Autoregressive Large Language Models (LLMs) frequently struggle with deterministic multi-step algorithmic tasks such as multi-digit multiplication and l
arXiv:2610.09726v1 Announce Type: new Abstract: Estimating remaining shelf life (RSL) from images could provide affordable decision support for perishable produce, but evaluation protocols can substan
arXiv:2610.09873v1 Announce Type: new Abstract: Binary Neural Networks (BNNs) enable efficient deep learning deployment on resource constrained devices with weights and activations compressed to one b
arXiv:2610.10058v1 Announce Type: new Abstract: Repeated queries over shared documents incur redundant encoding, while caching model states introduces persistent storage costs. Building on CoMem's int
arXiv:2610.09127v1 Announce Type: cross Abstract: Reconstructing an editable CAD model from a 3D shape remains a challenging engineering task. Existing methods can propose CAD operations, but no singl
arXiv:2610.09363v1 Announce Type: new Abstract: Contrails are the thin ice clouds that aircraft leave behind. They cause a large share of aviation's warming, and rerouting the few flights that produce
arXiv:2610.09291v1 Announce Type: new Abstract: Achieving human-level dexterity in complex, unstructured environments requires the seamless integration of whole-body scene interaction and dexterous ob
arXiv:2610.09552v1 Announce Type: cross Abstract: Watermarking enables language model providers to identify text generated by their models. However, its desired properties can conflict (ie~stronger wa
arXiv:2610.10068v1 Announce Type: new Abstract: Tabular data underpin prediction and decision-making in medicine, finance, government and science, but often contain sensitive individual-level informat
arXiv:2605.06380v2 Announce Type: replace Abstract: The topology of a classifier's decision regions determines how inputs with the same predicted label can be connected and deformed without changing t
arXiv:2610.10322v1 Announce Type: new Abstract: Recent methods have made promising progress in generating interactions between two humanoids, largely relying on physics-based tracking policies to conv
arXiv:2610.09863v1 Announce Type: new Abstract: Standard information retrieval metrics, such as mean Average Precision (mAP), assess performance one query at a time, based on how the similarities betw