Knowledge catalogue
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:2603.15106v2 Announce Type: cross Abstract: Enabling efficient deep neural network (DNN) inference on edge devices with different hardware constraints is a challenging task that typically requir
arXiv:2609.36540v1 Announce Type: new Abstract: Generalist robot policies such as vision-language-action models (VLAs) have achieved remarkable generalization, but their inference delays can conflict
Ollama’s new limits and max plans are worrying me, so I’ve been going harder on my harness. (Thanks to everyone who’s signed up for the waitlist so far.) Wanted to share how my v1.10.0 will dramatical
arXiv:2609.36525v1 Announce Type: cross Abstract: Distributed inference has become an indispensable part of deploying medical models under practical latency, memory, and throughput constraints. Althou
arXiv:2609.35867v1 Announce Type: new Abstract: We propose ReLOBGen, a method for generating limit order book (LOB) messages that are replayable by construction. Replayability is required for closed-l
arXiv:2609.36916v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) incur high inference latency from long visual token sequences. Existing pruning methods commonly use attention
arXiv:2609.38072v1 Announce Type: new Abstract: Ultra-high-resolution (UHR) remote sensing visual question answering (VQA) requires models to resolve small visual evidence within extremely large image
arXiv:2609.36590v1 Announce Type: new Abstract: Self-speculative decoding accelerates large language model (LLM) inference by drafting tokens from the target model itself, but faces a sharp tradeoff b
arXiv:2609.37581v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) excel at visual understanding and reasoning but often incur substantial inference costs due to the large number of visua
arXiv:2609.36529v1 Announce Type: cross Abstract: Recurrent neural networks (RNNs) compress the historical context into a memory state of fixed size, thus allowing for constant-time inference. The mem
arXiv:2609.36980v1 Announce Type: new Abstract: Despite recent advances in accuracy and efficiency, coarse matching remains an indispensable yet costly stage in existing semi-dense matchers due to den
Written by: Robin Grunewald, Supriya Mazumdar, Kelli Vanderlee Introduction Google Threat Intelligence Group (GTIG) examines vulnerability disclosure and exploitation statistics to evaluate the impact
arXiv:2609.36398v1 Announce Type: cross Abstract: Generative models make molecular crystal structure prediction fast, but their samples still exhibit geometric and packing violations. Physics can be i
arXiv:2609.37687v1 Announce Type: new Abstract: Active test-time adaptation (ATTA) improves robustness under distribution shift by updating a deployed model during inference while selectively querying
arXiv:2609.38121v1 Announce Type: new Abstract: KV cache memory and bandwidth costs grow with context length and batch size, which limits efficient long-context inference. To address this bottleneck,
arXiv:2609.33708v1 Announce Type: new Abstract: How does compositional reasoning emerge during learning? We address this question by mathematically analyzing the learning dynamics of deep linear netwo
arXiv:2609.32913v1 Announce Type: new Abstract: Recent progress in frontier models has renewed interest in large-scale reinforcement learning (RL), but the cost of generating large-model rollouts make
arXiv:2609.35060v1 Announce Type: new Abstract: Inferring dynamics from snapshots of evolving distributions is fundamentally underdetermined: the Fokker-Planck equation constrains the drift F only thr
GPT‑6.1 Sol is now generally available on Amazon Bedrock, providing enhanced reasoning for coding, computer use, and professional workflows. It runs on a high‑performance inference engine optimized fo
arXiv:2609.32570v1 Announce Type: new Abstract: Clustering algorithms that operate on nearest-neighbor graphs, such as FINCH (First Integer Neighbor Clustering Hierarchy), depend heavily on the qualit
arXiv:2609.35621v1 Announce Type: new Abstract: Serving long documents to a Large Language Model (LLM) repeatedly is expensive: computations grow with context length, and the memory footprint of the k
arXiv:2609.34638v1 Announce Type: new Abstract: Test-time adaptation (TTA) is a promising paradigm for handling distribution shift in time-series forecasting (TSF), where models adapt at inference tim
arXiv:2604.05137v2 Announce Type: replace-cross Abstract: Large language models (LLMs) can generate functionally correct programs that differ substantially in execution efficiency. Existing inference-
arXiv:2609.35368v1 Announce Type: new Abstract: Exo-to-egocentric video generation aims to synthesize what a person sees from their own viewpoint given third-person footage and a target head trajector
arXiv:2609.33101v1 Announce Type: cross Abstract: Little is known about how to manually design agents capable of dexterous manipulation. Some design principles have been inferred from close examinatio
arXiv:2609.34488v1 Announce Type: new Abstract: Looped architectures scale computation by reusing the same parameters across recurrent steps, and recent work shows that they substantially improve deep
arXiv:2609.33723v1 Announce Type: new Abstract: Diffusion transformers incur substantial inference cost through repeated model evaluations along a sampling trajectory. We introduce GeoShrink, a traini
arXiv:2609.34174v1 Announce Type: new Abstract: Test-time training (TTT) allows a model to improve its predictions at inference time by updating weights after every observed token. However, sequential
arXiv:2609.31924v1 Announce Type: new Abstract: Contact-rich manipulation depends on force sensing that is hard to infer from visual signals alone, both for collecting demonstrations and for training
arXiv:2609.34431v1 Announce Type: new Abstract: Conditional Flow Matching (CFM) models for text-to-speech (TTS) suffer from incoherent frequency evolution during inference. While similar spectral imba
arXiv:2609.33352v1 Announce Type: new Abstract: Set-valued classifiers, whether derived from precise probabilities and an adapted cost function, from convex sets with a robust inference mechanism, or
arXiv:2609.33986v1 Announce Type: new Abstract: In some multi-agent systems, the quantity to be optimized is not an externally specified reward but the information acquired about unknown properties of
arXiv:2609.33235v1 Announce Type: new Abstract: Implicit object properties that are difficult to directly infer from vision, such as material, container contents, or softness, can be revealed through
arXiv:2609.32854v1 Announce Type: new Abstract: Deep Differentiable Logic Gate Networks (LGNs) and Lookup Table Networks (LUTNs) offer a promising approach for very low power inference due to their us
arXiv:2609.34218v1 Announce Type: new Abstract: Looped language models separate computational depth from parameter count by repeatedly applying the same transformer block. Adapting these models requir
arXiv:2609.32839v1 Announce Type: cross Abstract: Recommender systems rely heavily on heterogeneous behavioral feedback to infer user preference. Although abundant, these signals are imperfect measure
arXiv:2609.33120v1 Announce Type: new Abstract: Electrical distribution grid operations require inference across heterogeneous networks from sparse, noisy, and incomplete time series measurements. In
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:2609.32897v1 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:2609.35579v1 Announce Type: new Abstract: Residual stream pruning methods reduce inference cost by shrinking the model's hidden dimension, but existing approaches typically choose these dimensio
arXiv:2609.33857v1 Announce Type: new Abstract: Recovering hidden transport mechanisms from sparse spatiotemporal observations is a fundamental inverse problem in scientific machine learning. In brain
arXiv:2609.32659v1 Announce Type: new Abstract: Quantization-Aware Pre-Training (QAPT) can increase the inference efficiency of DNNs, but a problematic behaviour known as rounding boundary weight osci
arXiv:2609.32836v1 Announce Type: cross Abstract: Radiomap blind prediction aims to infer radiomaps from observable representations of the propagation environment and base station configuration withou
arXiv:2609.33854v1 Announce Type: new Abstract: Driving policies require capabilities of scene understanding and future evolution prediction. To achieve this goal, current end-to-end models typically
arXiv:2609.33304v1 Announce Type: new Abstract: Personal Graphical User Interface (GUI) agents rely on interaction history to infer what a user wants from ambiguous instructions and to anticipate recu
arXiv:2609.34942v1 Announce Type: new Abstract: The inference efficiency of Multimodal Large Language Models (MLLMs) is severely constrained by massive visual token sequences induced by high-resolutio
arXiv:2609.35394v1 Announce Type: new Abstract: Video Large Language Models (Video LLMs) have achieved remarkable progress in video understanding, but their inference efficiency is constrained by the
arXiv:2609.32755v1 Announce Type: cross Abstract: Audio autoencoders compress waveforms into compact latent representations that serve as the interface between raw audio and downstream models. Current
arXiv:2609.32268v1 Announce Type: new Abstract: Standard autoencoder (AE) inference uses a single encoder-decoder pass, though the latent may not be optimal for each sample under a fixed decoder. We a
arXiv:2609.32197v1 Announce Type: cross Abstract: Diffusion Transformers have become the dominant architecture for video generation. Their substantial computational cost motivates scaling inference ac
arXiv:2510.05632v2 Announce Type: replace-cross Abstract: With the widespread adoption of Large Language Models (LLMs), the demand for high-performance LLM inference services continues to grow. Multi-
arXiv:2609.31682v1 Announce Type: new Abstract: More than 80 countries have reported malaria cases with 610 thousand deaths and are projected to increase. Identifying malaria early and accurately help
arXiv:2609.33968v1 Announce Type: cross Abstract: Testing whether two populations of networks share the same edge probabilities is a basic problem in network inference. How hard it is depends on the n
arXiv:2609.32518v1 Announce Type: new Abstract: Distilling bidirectional multi-step video diffusion transformers into few-step causal models has become a common approach for streaming video generation
arXiv:2609.31678v1 Announce Type: new Abstract: KV cache compression is widely used for long context LLM inference under memory constraints, while deployed systems typically score refusals after gener
arXiv:2609.32898v1 Announce Type: new Abstract: Pretrained tabular foundation models process every dataset at a fixed depth, with inference costs growing with dataset size. To address this, we present
arXiv:2609.33312v1 Announce Type: cross Abstract: Moving ML-mediated decision making onto privacy-preserving clients decentralises the economic decision along with the inference. Shared budget constra
arXiv:2609.34159v1 Announce Type: cross Abstract: World models infer latent states of an environment to capture its underlying dynamics and predict future evolution. Many real-world environments, howe