On State Reduction in Linear Attention
arXiv:2602.04852v3 Announce Type: replace Abstract: Linear attention offers a computationally efficient yet expressive alternative to softmax attention. However, recent empirical results indicate that
Knowledge catalogue
arXiv:2602.04852v3 Announce Type: replace Abstract: Linear attention offers a computationally efficient yet expressive alternative to softmax attention. However, recent empirical results indicate that
arXiv:2609.37575v1 Announce Type: cross Abstract: We argue that dividing codec design into Coding for Machines (CfM) and Coding for Humans (CfH) is a misleading distinction for deciding what informati
arXiv:2405.14749v3 Announce Type: replace-cross Abstract: Risk-sensitive reinforcement learning (RL) is crucial for maintaining reliable performance in high-stakes applications. While traditional RL m
arXiv:2506.03911v2 Announce Type: replace Abstract: Points-based rewards programs are a prevalent way to incentivize customer loyalty. In theory, the effective design of these programs is shaped by tw
arXiv:2609.36210v1 Announce Type: cross Abstract: Generative denoising models, such as diffusion and flow-matching, learn to sample from complex distributions by training a deep neural network denoise
arXiv:2609.37974v1 Announce Type: cross Abstract: Masked diffusion models (MDMs) generate text by unmasking several tokens per step, but they are trained and sampled under different conditions. The mo
arXiv:2609.36413v1 Announce Type: new Abstract: A pretrained video world model admits many plausible futures for a scene, but a robot must realize the exact task-conditioned one. To turn world models
arXiv:2609.36101v1 Announce Type: cross Abstract: Contrastive vision-language models learn shared embedding spaces by aligning matched image-text pairs, yet their representations remain separated by a
arXiv:2609.34879v2 Announce Type: replace Abstract: Tool agents use large language models to act through external tools, yet successfully executed calls can still leave user requests unfulfilled. Tool
arXiv:2609.36227v1 Announce Type: cross Abstract: Next-latent prediction fits a map from the current embedding to the next one. LeNEPA carries this objective to time series, replacing the stop-gradien
arXiv:2609.37861v1 Announce Type: new Abstract: In the Global South, the lower-income countries of Africa, Asia, and Latin America where most of the world's languages are spoken, a deployed text class
arXiv:2609.36442v1 Announce Type: cross Abstract: Continual learning enables vision systems to adapt to ever-changing data distributions. Despite significant advances, existing approaches fail to capt
arXiv:2604.05468v3 Announce Type: replace Abstract: Temporal knowledge graph (TKG) extrapolation is an important task that aims to predict future facts through historical interaction information withi
arXiv:2609.35799v1 Announce Type: new Abstract: In July 2026, OpenAI's agents coordinated over channels outside their intended environment to breach Hugging Face's secured infrastructure. Could existi
arXiv:2609.37011v1 Announce Type: cross Abstract: Federated learning enables multiple clients to collaboratively train models without sharing their private data. However, the lack of visibility into l
arXiv:2609.37221v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed to solve complex scientific and practical problems via iterative optimization. However, dynamical
arXiv:2609.36486v1 Announce Type: new Abstract: We study an unknown-transition finite-horizon Markov decision process (MDP) with a finite collection of known reward functions {r^1, r^2, ldots, r^M}. T
arXiv:2609.38073v1 Announce Type: cross Abstract: We study exact learning with membership queries for concept classes mathcal Csubseteq{0,1}^N, focusing on the relationships among their deterministic,
arXiv:2606.19302v2 Announce Type: replace-cross Abstract: As deep learning for physical systems continues to grow in popularity, efforts to improve generalizability have primarily focused on designing
arXiv:2405.07944v1 Announce Type: cross Abstract: Among the well-known methods to approximate derivatives of expectancies computed by Monte-Carlo simulations, averages of pathwise derivatives are ofte
arXiv:2609.37745v1 Announce Type: new Abstract: Neural scaling, in which loss falls as a power law with training, is central to large language models, and one recent proposal is that a 1/3 exponent em
arXiv:2609.37986v1 Announce Type: new Abstract: Recovering articulated 4D representations of animals from monocular videos remains challenging due to the large diversity of quadruped morphologies and
arXiv:2609.37579v1 Announce Type: cross Abstract: Bresar and Mijatovic ite{bresar2025} show that Ornstein--Uhlenbeck diffusion is hard to beat in forward convergence under assumptions that exclude sup
arXiv:2609.37564v1 Announce Type: new Abstract: Merging pretrained models has emerged as an effective approach for consolidating diverse capabilities into a single unified model. However, prevailing m
arXiv:2609.36602v1 Announce Type: new Abstract: Transferring human motion to humanoid robots requires adapting the demonstrated motion to the robot morphology while preserving interactions with the en
arXiv:2609.36264v1 Announce Type: new Abstract: Reliable evaluation of large language models (LLMs) is essential for their development and deployment, yet is often costly, risky, and difficult to perf
arXiv:2609.36374v1 Announce Type: new Abstract: Feed-forward 3D reconstruction models have achieved impressive performance by scaling model and dataset size, but their cost excludes most research grou
arXiv:2609.37915v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) trains a student to match a privileged teacher distribution along its own sampled trajectory. Standard OPSD applies
arXiv:2609.35865v1 Announce Type: cross Abstract: Single-token typed-decision models answer a schema question by reading the logits of a few one-letter answer codes at a single position: they are fast
arXiv:2609.36086v1 Announce Type: cross Abstract: Language models are frequently employed to evaluate other language models. An LM evaluator scoring agentic behaviors across multiple criteria is valua
arXiv:2609.37685v1 Announce Type: new Abstract: Language-aligned and self-supervised visual encoders offer complementary strengths in semantic abstraction and spatial detail. Harnessing this complemen
arXiv:2609.37577v1 Announce Type: new Abstract: Large Language Model judges are widely used to rank texts and text-generating systems through pairwise comparison, and their reliability is typically as
arXiv:2609.36263v1 Announce Type: cross Abstract: Existing multimodal scaling laws fit multimodality terms empirically after testing and never vary how much data is multimodally paired at fixed data b
arXiv:2609.37323v1 Announce Type: new Abstract: Discrete diffusion models have emerged as a powerful paradigm for solving combinatorial optimization (CO) problems on graphs by learning to sample high-
arXiv:2609.37001v1 Announce Type: cross Abstract: Diffusion Transformers (DiTs) enable high-quality video generation but suffer from substantial inference latency, primarily attributable to the comput
arXiv:2609.35935v1 Announce Type: new Abstract: Learning energy-efficient humanoid locomotion requires discovering mechanically economical gait coordination, not merely reducing actuator effort. Reinf
arXiv:2609.37921v1 Announce Type: new Abstract: What are the inductive biases of a Transformer architecture? Existing theory on how the forward pass shapes representations either considers whether Tra
arXiv:2609.37350v1 Announce Type: new Abstract: The development of AI systems for tumor-specific applications is limited by the scarcity of labeled data. Synthetic tumor inpainting offers a promising
arXiv:2609.36521v2 Announce Type: new Abstract: Physical-field reconstruction and forecasting depend on both measurement density and spatial layout, yet evaluation under a single observation pattern d
arXiv:2609.38023v1 Announce Type: new Abstract: Physics-Informed Neural Networks (PINNs) embed governing equations into deep learning, but enforce them only through loss residuals, leaving highly osci
arXiv:2609.36638v1 Announce Type: cross Abstract: Text-to-image users often provide concise and underspecified prompts, whereas generative models benefit from detailed textual conditions for reliable
arXiv:2609.36322v1 Announce Type: cross Abstract: Chunked KV-cache compression reduces the memory and attention costs of long-context inference by compressing windows of consecutive tokens into fewer
arXiv:2609.36014v1 Announce Type: new Abstract: Pixel-space diffusion Transformers (DiTs) directly operate on high-dimensional visual data, yet their hidden representations typically undergo uniform r
arXiv:2601.01207v2 Announce Type: replace Abstract: In stochastic message passing, an edge's sampled role changes the node states used to compute adaptive weights at later layers. Weight averaging the
arXiv:2609.36388v1 Announce Type: new Abstract: An activation-steering coefficient sets intervention strength, but requesting a particular degree of persona expression requires a behavioral scale. We
arXiv:2602.03915v2 Announce Type: replace-cross Abstract: Tokens are discrete representations that allow modern deep learning to scale by transforming high-dimensional data into sequences that can be
arXiv:2609.36087v1 Announce Type: cross Abstract: Clinicians and neuroscientists have long analyzed intracranial electroencephalography (iEEG) through directly measurable physiological characteristics
arXiv:2609.37609v1 Announce Type: new Abstract: Magnetohydrodynamics (MHD) is central to plasma modeling in astrophysics, space science, fusion, and engineering, but resolving multiscale MHD dynamics
arXiv:2609.36193v1 Announce Type: new Abstract: Learning from scientific measurements often requires aligning modalities with different spatial support and resolution. Subsurface characterization is a
arXiv:2609.37525v1 Announce Type: new Abstract: Physical neural networks and analog in-memory computing could reduce the energy cost of neural network training. Realizing this potential, however, requ
arXiv:2609.36633v1 Announce Type: new Abstract: This paper proposes a physics-guided gradient-ascent-based machine unlearning method that couples the forgetting signal with the physical residual of th
arXiv:2609.37487v1 Announce Type: new Abstract: Precipitation nowcasting, generating future radar fields from past observations, is critical for flood warning and disaster response. It is also a deman
arXiv:2609.37022v1 Announce Type: new Abstract: Efficient patient flow coordination across autonomous hospital departments is critical for mitigating overcrowding and balancing resource utilization. W
arXiv:2609.37970v1 Announce Type: cross Abstract: World-action models (WAMs) jointly predict how a scene will evolve and how an agent should act, however joint generation alone does not necessarily im
arXiv:2609.36326v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) hands the user's query to whoever hosts the corpus. We propose PILLAR, a Privacy-Preserving RAG (PPRAG) system base
arXiv:2511.22435v2 Announce Type: replace Abstract: Invariant learning on graphs aims to build predictors that rely on causal substructures rather than on environment-specific shortcuts. Current metho
arXiv:2609.37809v1 Announce Type: cross Abstract: Predicting canopy height from medium-resolution satellite imagery is a common and scalable approach for assessing the condition of the world's forests
arXiv:2609.36607v1 Announce Type: new Abstract: Remote photoplethysmography (rPPG) offers a promising non-contact solution for heart rate monitoring, yet its real-world robustness is fundamentally lim
arXiv:2609.37907v1 Announce Type: new Abstract: Video games offer scalable environments for studying perception and control in embodied agents.Abundant online gameplay videos could supply demonstratio
arXiv:2609.37784v1 Announce Type: new Abstract: Satellite observations, precomputed embeddings, and map products describe the same evolving Earth, yet are stored as independent, petabyte-scale data pr