Knowledge catalogue
arXiv:2610.04606v1 Announce Type: new Abstract: We present a 4D Gaussian Splatting framework for the Sparse-View Track of the SIGGRAPH Asia 2026 Volumetric Video Challenge, which requires dynamic scen
arXiv:2610.05891v1 Announce Type: new Abstract: Post-hoc class activation maps (CAMs) are a standard tool for inspecting the evidence behind an image classifier's predictions, yet nothing in ordinary
arXiv:2610.06413v1 Announce Type: new Abstract: Thinking-enabled vision-language models (VLMs) report ever-higher accuracy on spatial benchmarks, yet final-answer scores cannot reveal whether a correc
arXiv:2610.06315v1 Announce Type: new Abstract: Electroencephalography (EEG) based brain-computer interfaces enable direct brain-to-device communication for applications such as rehabilitation and com
arXiv:2610.04875v1 Announce Type: cross Abstract: Diffusion large language models (DLLMs) generate text through iterative block denoising, and multi-branch speculative decoding accelerates this proces
arXiv:2610.04413v1 Announce Type: new Abstract: We develop a principled framework for constructing neural networks whose specific parameter realizations admit an explicit algorithmic interpretation. E
arXiv:2510.14217v3 Announce Type: replace Abstract: The spectral properties of feature embeddings offer critical insights into model generalization and representation quality. While deep learning mode
arXiv:2610.06012v1 Announce Type: new Abstract: In this work, we study transformer attention through the lens of spectral geometry and operator theory. We view each attention head as a functional map
arXiv:2610.06334v1 Announce Type: new Abstract: Diffusion models have greatly advanced instruction-guided image editing, while also raising concerns about unauthorized image manipulation. Image immuni
arXiv:2610.05688v1 Announce Type: new Abstract: We study adversarial multiplayer bandits with K arms and 2le m<K labeled players, without collision information, shared randomness, or an external commu
arXiv:2601.19730v2 Announce Type: replace Abstract: The empirical evidence indicates that stochastic optimization with heavy-tailed gradient noise is more appropriate to characterize the training of m
arXiv:2610.06344v1 Announce Type: new Abstract: In deep graph neural networks, increasing depth enlarges the receptive field but often leads to over-smoothing, where node representations tend to align
arXiv:2610.05664v1 Announce Type: new Abstract: Vision-and-Language Navigation (VLN) policies increasingly benefit from strong semantic priors provided by large vision-language models (VLMs). However,
arXiv:2610.05977v1 Announce Type: new Abstract: Serving a large language model (LLM) across a fleet of deployments requires several weight-precision operating points. Multi-precision formats serve the
arXiv:2610.04912v1 Announce Type: cross Abstract: Language models increasingly serve prompts that carry private data, and secure inference under homomorphic encryption lets a client outsource the comp
arXiv:2610.06198v1 Announce Type: new Abstract: Cutting is a recurring operation in robotic au tomation, from food preparation to surgical tissue resection. For highly compliant targets, blade motion
arXiv:2610.05576v1 Announce Type: new Abstract: Stochastic order-independent transparency enables efficient and elegant rendering of primitive-based radiance fields like 3D Gaussian Splatting models,
arXiv:2610.06383v1 Announce Type: new Abstract: Inference-time steering offers cheap, fine-grained control over a language model's outputs by estimating a concept's representation in activation space
arXiv:2610.03799v1 Announce Type: new Abstract: Recovering executable CAD programs from 3D meshes is challenging due to the compositional nature of CAD construction and the interaction between discret
arXiv:2602.02180v2 Announce Type: replace Abstract: Linearizing pretrained large language models (LLMs) primarily relies on intra-layer hybrid attention mechanisms to alleviate the quadratic complexit
arXiv:2610.04241v1 Announce Type: new Abstract: Fourier Neural Operators (FNOs) offer an efficient paradigm for solving partial differential equations (PDEs). However, FNOs rely on a fixed Fourier bas
arXiv:2610.05961v1 Announce Type: new Abstract: Valuing player actions in football requires accounting for strategic interactions among 22 players, including off-ball movements and defensive positioni
arXiv:2610.03873v1 Announce Type: new Abstract: Text-driven human motion generation has advanced substantially, yet most methods assume instructions are available before synthesis. Interactive applica
arXiv:2610.05939v1 Announce Type: cross Abstract: This paper establishes the first general structural solution to the problem of state estimation for nonlinear systems driven by unknown inputs. Buildi
arXiv:2610.03743v1 Announce Type: cross Abstract: Accurate modeling of the daily evolution of sea ice concentration (SIC) is central to improving the credibility and operational forecasting capability
arXiv:2610.06211v1 Announce Type: new Abstract: Learned models for industrial control are usually judged by aggregate accuracy, but accuracy at the component level does not guarantee safety once it is
arXiv:2505.24033v3 Announce Type: replace-cross Abstract: We investigate whether hidden states from Structured State Space Models (SSMs) can be merged post hoc to support downstream reasoning. Inspire
arXiv:2610.04009v1 Announce Type: cross Abstract: Vision-language-action models (VLAs) inherit strong semantic grounding from pretrained vision-language backbones but are typically optimized for predi
arXiv:2610.04781v1 Announce Type: new Abstract: In an image latent space, the embeddings of high-resolution, natural, and sharp images form a manifold. Degradation of high-resolution images pushes the
arXiv:2604.01279v2 Announce Type: replace Abstract: We introduce Sven (Singular Value dEsceNt), a new optimization algorithm for neural networks that exploits the natural decomposition of loss functio
arXiv:2610.05270v1 Announce Type: cross Abstract: This paper investigates the real-time dispatch of a shared drone fleet for on-demand food delivery and urban road network monitoring. We consider a co
arXiv:2610.03947v1 Announce Type: new Abstract: Finding a compact formula that fits a set of input-output pairs and predicts outputs on unseen inputs is a fundamental problem in science. Symbolic regr
arXiv:2610.04335v1 Announce Type: new Abstract: Remote pose estimation of noncooperative Unmanned Aerial Vehicles (UAVs) from imagery is critical, as they cannot be influenced or instrumented in advan
arXiv:2601.02799v3 Announce Type: replace Abstract: Uniform-noise discrete diffusion and flow models generate sequences non-autoregressively through iterative, context-dependent token replacements. Ho
arXiv:2610.05731v1 Announce Type: new Abstract: Earth observation (EO) data provide rich temporal supervision, yet existing remote sensing foundation models mainly exploit sequential observations thro
arXiv:2610.03828v1 Announce Type: new Abstract: Quadruped robots entering hospitals, care homes, and quiet offices must be context-appropriate not only in where they move but in how loudly they move:
arXiv:2610.05583v1 Announce Type: new Abstract: Passive leader arms transmit an operator's motion without returning remote contact or load cues. TacGELLO uses the existing servos of a 3D-printed leade
arXiv:2610.04896v1 Announce Type: new Abstract: Robotic controllers increasingly rely on analytical models, simulators, cost-query interfaces, and learned world models. However, physical deployment ca
arXiv:2610.04363v1 Announce Type: new Abstract: Learning contact-rich dexterous manipulation from human demonstrations provides a scalable source of interaction data, yet transferring such skills to r
arXiv:2610.03773v1 Announce Type: cross Abstract: Soft tactile sensors elevate robotic touch through enhanced flexibility and adaptability, yet most existing designs depend on embedded electronics tha
arXiv:2610.06658v1 Announce Type: new Abstract: In daily life, each person exhibits unique speaking habits, leading to subtle yet consistent lip-shape variations even when pronouncing the same word. A
arXiv:2610.06153v1 Announce Type: new Abstract: Expressive humanoid interaction requires speech, facial animation, and body gestures to form a coherent response. However, many full-body humanoid robot
arXiv:2610.04529v1 Announce Type: new Abstract: Text-driven motion editing modifies an existing motion sequence according to a text instruction while preserving the content of the source motion. Exist
arXiv:2610.06814v1 Announce Type: new Abstract: World models learn to predict how their environment will evolve, making them an important foundation for general-purpose robotic control. Yet world acti
arXiv:2610.04467v1 Announce Type: new Abstract: Large language models (LLMs) remain highly vulnerable to jailbreak attacks that induce harmful behaviors and circumvent safety alignment. To defend agai
arXiv:2610.03824v1 Announce Type: cross Abstract: Treatment efficacy is traditionally demonstrated on the basis of a single primary outcome. However, clinical decision-making usually requires consider
arXiv:2606.16978v2 Announce Type: replace-cross Abstract: For residual learning that refines existing behavior, sample efficiency depends on two things: how much information each rollout returns, and
arXiv:2610.05350v1 Announce Type: new Abstract: Behavioral Foundation Models (BFMs) aim to solve a wide range of downstream tasks without test-time policy learning by inferring a task vector from the
arXiv:2610.04627v1 Announce Type: new Abstract: Object detection under image degradation can benefit from clean-image supervision, but aggregate gains do not imply that transferred representation chan
arXiv:2610.05402v1 Announce Type: new Abstract: A central challenge in continual learning is to acquire new knowledge without forgetting what the model has already learned. This challenge appears in l
arXiv:2610.05896v1 Announce Type: new Abstract: Rapid progress in video generation has led to a plethora of models that differ substantially in capability and generation cost. This raises a natural qu
arXiv:2610.05456v1 Announce Type: cross Abstract: In Networked Markov Decision Processes, transition dynamics are often unknown and the state--action space grows rapidly with the number of agents. In
arXiv:2602.14174v2 Announce Type: replace Abstract: Contact-rich manipulation requires robots to regulate both motion and interaction forces, yet achieving adaptive compliance remains a fundamental ch
arXiv:2610.03984v1 Announce Type: cross Abstract: Autonomous coding agents solve repository issues by reading code, running commands, editing files, and submitting patches. Extra inference-time comput
arXiv:2610.05949v1 Announce Type: new Abstract: Site-specific fertilizer recommendation systems adapt nutrient advice to location, soil properties, crop type, and production targets, but scientific re
arXiv:2610.04945v1 Announce Type: new Abstract: Destructive single-cell measurements provide unpaired population snapshots rather than observations of the same cells across conditions. Local cell stat
arXiv:2604.07685v2 Announce Type: replace Abstract: Identifying governing equations of nonlinear dynamical systems from data is challenging. While sparse identification of nonlinear dynamics (SINDy) a
arXiv:2610.04144v1 Announce Type: new Abstract: Locomotion on granular slopes such as sand dunes remains a fundamental challenge for legged robots due to reduced shear strength and gravity-induced ani
arXiv:2610.04701v1 Announce Type: new Abstract: Memory is essential for long-horizon robotic manipulation, where successful actions may depend on past events that are no longer recoverable from the cu
arXiv:2008.06006v5 Announce Type: replace-cross Abstract: In this paper, we propose Textual Echo Cancellation (TEC) - a framework for cancelling the text-to-speech (TTS) playback echo from overlapping