Knowledge catalogue
arXiv:2609.32322v1 Announce Type: new Abstract: World models are typically trained and evaluated by prediction error, assuming that more accurate predictions lead to better decisions. We show that thi
arXiv:2609.35072v1 Announce Type: new Abstract: We consider the problem of trajectory valuation in reinforcement learning: how to identify and mitigate detrimental trajectories during online training.
arXiv:2609.32597v1 Announce Type: new Abstract: Symbolic regression (SR) aims to discover compact and meaningful mathematical equations from data, but searching the vast combinatorial space of symboli
arXiv:2609.33164v1 Announce Type: cross Abstract: In these notes, we view control as a dynamically constrained sampling problem on the state-space of a control system. With this viewpoint, we extend m
arXiv:2609.34572v1 Announce Type: cross Abstract: Reasoning language models that can call tools must decide during inference whether to answer unaided or delegate. Any self-reflection mechanism for th
arXiv:2609.34986v1 Announce Type: cross Abstract: We describe the Nurnberg NLP system for ChildSafeAds 2026. The shared task asks what a monitoring system for commercial content in child-facing YouTub
arXiv:2609.33076v1 Announce Type: new Abstract: Nutrition estimation is a fundamental task in consumer diet tracking, clinical dietetics, chronic disease management, sports and hospital nutrition, and
arXiv:2609.33681v1 Announce Type: new Abstract: This paper presents the application and experimental evaluation of a systematic method for optimal sensor placement in soft robots. Existing methods eit
arXiv:2609.33100v1 Announce Type: new Abstract: Video models commonly use uniform grids even though visual complexity varies substantially across space and time. We introduce OctVideo, which approxima
arXiv:2609.33186v1 Announce Type: cross Abstract: Evaluating a target policy using data generated by a different behavior policy remains a fundamental challenge in reinforcement learning. While most e
arXiv:2609.31714v1 Announce Type: new Abstract: Building omni-modal models with physical intelligence requires fine-grained supervision that captures physical evidence such as contact, support, deform
arXiv:2609.32780v1 Announce Type: new Abstract: Vision-language models (VLMs) increasingly use sparse mixture-of-experts (MoE) to scale language-side computation, yet visual information is typically r
arXiv:2609.32569v1 Announce Type: new Abstract: Smart-home assistants are expected to handle diverse, realistic requests that arise in daily life. In such interactions, users often rely on the surroun
arXiv:2609.34653v1 Announce Type: cross Abstract: On-device streaming omni-modal inference safeguards user privacy and eliminates prohibitive per-token API costs, but faces a critical bottleneck: the
arXiv:2603.24458v3 Announce Type: replace Abstract: While proprietary systems such as Seedance-2.0 have achieved remarkable success in omni-capable video generation, the academic research community la
arXiv:2609.31631v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models enable efficient scaling of large language models but face critical deployment challenges due to massive memory requirem
arXiv:2512.06983v2 Announce Type: replace-cross Abstract: World models enable agents to plan within imagined environments by predicting future states conditioned on past observations and actions. Howe
arXiv:2609.34549v1 Announce Type: new Abstract: Parameter space symmetries and conservation laws play an important role in understanding the loss landscapes and implicit biases of neural networks. Ins
arXiv:2609.31947v1 Announce Type: new Abstract: Hybrid transformer architectures that replace most softmax attention layers with linear attention offer transformer-level quality at a fraction of the m
arXiv:2609.35259v1 Announce Type: new Abstract: On-policy learning has been argued to reduce catastrophic forgetting, produce sparser parameter updates, and improve generalisation. However, existing c
arXiv:2609.35611v1 Announce Type: new Abstract: Instruction-based image editing has achieved strong performance in single-turn settings, yet practical editing is often iterative, with each instruction
arXiv:2609.34806v1 Announce Type: cross Abstract: Reasoning about temporal structure of audio recordings requires Large Audio Language Models (LALMs) to associate sound events with their temporal posi
arXiv:2609.32302v1 Announce Type: new Abstract: Prompt engineering has become an indispensable tool for using large language models (LLMs), turning LLMs into task-specific experts without changing the
arXiv:2507.17725v3 Announce Type: replace-cross Abstract: As demands for resource efficiency and safety in modern neural networks intensify, substantial research effort has gone into model compression
arXiv:2609.34666v1 Announce Type: cross Abstract: Differentiable physics is increasingly used in robotic material manipulation for system identification, trajectory or skill optimization, demonstratio
arXiv:2505.11840v4 Announce Type: replace Abstract: As the default optimizer for training large language models, AdamW has achieved remarkable success in deep learning. However, its convergence behavi
arXiv:2609.32470v1 Announce Type: new Abstract: Large reasoning models (LRMs) often suffer from overconfidence when expressing their uncertainty. Confidence-aware reinforcement learning (RL) offers a
arXiv:2609.34423v1 Announce Type: new Abstract: Non-stationary online learning has attracted much attention in recent years, as static regret is insufficient to guide algorithm design in changing envi
arXiv:2609.33904v1 Announce Type: new Abstract: We consider the behavior of deterministic, full-batch, bias-corrected Adam in separable linear classification with softmax parametrization under log-los
arXiv:2609.33833v1 Announce Type: new Abstract: Adversarial attacks have long posed a fundamental threat to machine learning systems. As multimodal large language models (MLLMs) rapidly evolve and bec
arXiv:2609.31655v1 Announce Type: new Abstract: Generative priors reconstruct accelerated 3D MRI well but pay heavily at deployment: tens of network evaluations per volume, and protocol-specific hyper
arXiv:2609.32316v1 Announce Type: new Abstract: Traffic lights are a key regulatory signal for autonomous driving at urban intersections, yet existing traffic signal perception is still predominantly
arXiv:2609.35514v1 Announce Type: new Abstract: In ecology, psychometrics, and the analysis of social and financial networks, binary matrices are often analyzed conditional on their observed row and c
arXiv:2609.34321v1 Announce Type: new Abstract: GUI agents are deployed with frozen weights and discard everything they experience on the job. Existing ways to update an agent's weights assume somethi
arXiv:2609.34978v1 Announce Type: new Abstract: Consumer earbuds already stream inertial motion data from the head, one of the most widely worn sensor locations on the body. We ask how much of the 3D
arXiv:2609.34301v1 Announce Type: new Abstract: Drug design couples property evaluation, conditional generation, structure-based design, and local optimization, yet machine learning systems typically
arXiv:2609.32708v1 Announce Type: cross Abstract: Drifting models enable one-step generation by amortizing distribution transport into training, but this efficiency places greater demands on the trans
arXiv:2609.31670v1 Announce Type: new Abstract: Iterative and generative denoisers are increasingly used under the assumption that multi-step refinement outperforms a single regression pass. We show t
arXiv:2606.19253v2 Announce Type: replace Abstract: Existing approaches to 3D scene understanding in Vision-Language Models (VLMs) either rely on complex, model-specific geometry encoders or large tra
arXiv:2609.32175v1 Announce Type: new Abstract: Autoregressive video diffusion is a promising render-time fixer for 3D Gaussian Splatting (3DGS) in autonomous-driving simulation, but deployment demand
arXiv:2609.33090v1 Announce Type: cross Abstract: SLU encompasses a diverse set of tasks, including ISLR, CSLR, and SLT. Although these tasks share basic semantic and linguistic foundations, they are
arXiv:2609.33562v1 Announce Type: new Abstract: Systematic out-of-distribution (OOD) generation remains a critical bottleneck for continuous-time generative models. While standard joint classifier-fre
arXiv:2609.32343v1 Announce Type: new Abstract: Metal implants corrupt MRI measurements throughout k-space, yet existing accelerated MRI methods assume clean data and most metal artifact reduction app
arXiv:2609.32810v1 Announce Type: cross Abstract: Multidisciplinary tumor boards integrate multimodal clinical observations and longitudinal patient histories through specialist discussions, yet bench
arXiv:2609.33338v1 Announce Type: new Abstract: Referring video segmentation with heterogeneous multimodal queries---spanning text, audio, and reference images---demands both robust cross-modal unders
arXiv:2609.35052v1 Announce Type: new Abstract: Video world models must preserve the visual state of the world over time, but existing evaluation protocols often rely on generated histories, video ref
arXiv:2609.35537v1 Announce Type: new Abstract: We study information aggregation in the networked learning model introduced by Kearns, Roth, and Ryu (SODA 2026). There is a fixed distribution over d f
arXiv:2609.32949v1 Announce Type: new Abstract: We study online dynamic pricing with censored demand, where an arbitrary inventory level is revealed before pricing and may adapt to past observations,
arXiv:2609.33377v1 Announce Type: new Abstract: Deterministic neural networks and neural operators provide point predictions with no intrinsic measure of reliability. Yet, predictive uncertainty may s
arXiv:2609.31787v1 Announce Type: cross Abstract: Optimal Transport (OT) provides a principled framework for comparing and transforming probability distributions while preserving geometric structure.
arXiv:2609.34744v1 Announce Type: cross Abstract: To comply with recent regulations requiring traceable generated content, modern watermarking has adopted multi-bit post-hoc watermarking schemes. Thes
arXiv:2609.32897v1 Announce Type: new Abstract: Sampling-based motion planners guided by diffusion models produce high-quality trajectories in a single run, yet the stochastic diversity available at i
arXiv:2609.33927v1 Announce Type: new Abstract: This study explores the optimization of the Phi-2 Small Language Models (SLMs) for real-time chatbot applications through Parameter-Efficient Fine-Tunin
arXiv:2609.33760v1 Announce Type: new Abstract: We consider contextual binary prediction with i.i.d. contexts from an unknown distribution and adaptively chosen losses. We show that a simple Follow-th
arXiv:2609.32996v1 Announce Type: new Abstract: Policies trained from the same base model can appear to solve different problems. An oracle that chooses the best policy for each problem may therefore
arXiv:2609.34843v1 Announce Type: new Abstract: Audio-video generation using heterogeneous multimodal references has emerged as a new challenge, requiring both compositional control over generation an
arXiv:2409.19648v2 Announce Type: replace Abstract: Oriented object detection in remote sensing images is a challenging task due to objects being distributed in multi-orientation. Recently, end-to-end
arXiv:2609.34985v1 Announce Type: new Abstract: Multi-reward policy optimization requires a joint update that reflects both the learning signals and the intended relationships among objectives. We int
arXiv:2609.33194v1 Announce Type: new Abstract: Matrix-valued optimizers such as Muon exploit the spectral structure of neural network updates through Newton--Schulz orthogonalization, but their near-
arXiv:2609.33543v1 Announce Type: cross Abstract: Coupled rollouts can reduce the noise of counterfactual action comparisons, but two issues prevent standard common-random-number constructions from se