Knowledge catalogue
arXiv:2610.01014v1 Announce Type: new Abstract: Voting over multiple LLM responses is a common primitive in test-time scaling and ensemble inference. Collecting more responses can expand the candidate
arXiv:2610.01712v1 Announce Type: new Abstract: In-context learning (ICL) enables a pretrained model to infer a task from demonstrations without updating its parameters. While much of the existing the
arXiv:2610.00864v1 Announce Type: cross Abstract: In this paper, we study how to achieve one-step action generation in Robotic Foundation Models (RFMs), aiming to overcome the high inference latency o
arXiv:2610.00265v1 Announce Type: new Abstract: Large Language Bayes (LLB) answers an informal modelling question by sampling candidate probabilistic programs from a language model, running approximat
arXiv:2610.01905v1 Announce Type: new Abstract: Online vectorized HD map construction is essential for scaling safe autonomous driving and requires accurate, real-time inference. Prior methods typical
arXiv:2603.11546v2 Announce Type: replace Abstract: Many real-world machine learning tasks are anti-causal: they require inferring latent causes from observed effects. In practice, we often face multi
arXiv:2610.01434v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) incur substantial inference costs when processing long visual-textual sequences. While existing operation com
arXiv:2610.02207v1 Announce Type: cross Abstract: 3D Gaussian avatars support fast rendering, however, their real-time animation is often challenged by the costly neural inference. We address this bot
arXiv:2610.00558v1 Announce Type: new Abstract: While Mixture-of-Experts (MoE) models effectively scale model capacity through sparse activation, their deployment is often bottlenecked by prohibitive
arXiv:2610.00751v1 Announce Type: cross Abstract: Recent theoretical work identified fundamental properties of representation geometry that shape inference ability of deep neural networks. These inclu
arXiv:2610.01323v1 Announce Type: new Abstract: Safety-aligned large language models (LLMs) often refuse a harmful request but comply once the same goal is spread over several turns. Preference object
arXiv:2610.00373v1 Announce Type: new Abstract: Attention-head ablation, zeroing a head and measuring the resulting change in task performance, is a common method for inferring which components of a l
arXiv:2609.38364v1 Announce Type: cross Abstract: Discrete diffusion models and flow matching have emerged as powerful frameworks for generative modeling over discrete state spaces, yet efficient few-
arXiv:2609.38806v1 Announce Type: cross Abstract: Next-token prediction has driven remarkable progress in large language models, yet a growing body of evidence suggests that they can struggle on probl
arXiv:2609.38697v1 Announce Type: cross Abstract: We present Cascadia, a system for serving large language models on fleets of commodity Intel AIPCs using their CPU, integrated-GPU, and NPU resources.
arXiv:2609.39134v1 Announce Type: new Abstract: Visual-token compression improves the efficiency of large vision-language models, but can expose failures that full-token evaluation misses. We study ad
arXiv:2609.39859v1 Announce Type: new Abstract: Masked diffusion language models (dLLMs) have shown strong potential for faster inference through parallel token generation when combined with confidenc
arXiv:2609.39777v1 Announce Type: new Abstract: LLM-based multi-agent systems coordinate specialized reasoning through aggregation, interaction, and adaptive control, yet their potential for graph lea
arXiv:2410.02159v3 Announce Type: replace-cross Abstract: Language models (LMs) can 'memorize' information, i.e., encode training data in their weights in such a way that inference-time queries can le
arXiv:2609.38593v1 Announce Type: cross Abstract: Skills are external artifacts that Large Language Models (LLMs) consume at inference time to improve their performance on specialized domains by incor
arXiv:2609.36985v1 Announce Type: cross Abstract: The central challenge of world modeling is to learn representations that capture how the world evolves. However, existing world models predominantly r
Anthropic's Claude Opus 5, Claude Sonnet 5, and Claude Haiku 4.5 are now available in India through Amazon Bedrock geographic cross-Region inference. You can access these models while processing data
arXiv:2609.36835v1 Announce Type: new Abstract: Long-context large language model inference is bottlenecked by KV caches that grow linearly with sequence length. This burden is especially severe for l
arXiv:2609.35875v1 Announce Type: new Abstract: Multi-agent debate (MAD) reportedly improves reasoning and factuality over single-model inference, but prior work treats agents as symmetric peers, leav
arXiv:2501.18157v2 Announce Type: replace-cross Abstract: Building reliable speech systems often requires combining multiple modalities, like audio and visual cues. While such multimodal solutions fre
arXiv:2410.14127v2 Announce Type: replace-cross Abstract: A central question in human immunology is how a patient's T cell receptors impacts disease. Here, we introduce a method to infer the causal ef
arXiv:2609.38104v1 Announce Type: new Abstract: Power-sharpened sampling is an inference-time alternative to reinforcement-learning (RL) post-training for enhancing reasoning in large language models
arXiv:2609.36406v1 Announce Type: new Abstract: Cell Painting is a high-content morphological profiling assay widely used for phenotype-based biological inference, with mechanism of action (MOA) predi
arXiv:2609.37042v1 Announce Type: new Abstract: Video Large Language Models (VideoLLMs) have achieved strong video understanding capabilities but incur substantial inference overhead due to the large
arXiv:2609.36860v1 Announce Type: new Abstract: We present IronLLM-0.6B, a 654M-parameter language model designed for efficient on-device inference. IronLLM-0.6B combines a hybrid attention architectu
arXiv:2609.36826v1 Announce Type: new Abstract: Video generation models have demonstrated emerging zero-shot capabilities for visual reasoning, perception, and other vision tasks. However, diffusion-b
arXiv:2609.35873v1 Announce Type: new Abstract: Automated generation of LLM harnesses promises to improve inference through task specialization. Yet additional answer coverage can arise from repeated
arXiv:2609.36954v1 Announce Type: cross Abstract: Distributed inference depends on GPU collective communication that must keep pace with evolving hardware and specialized workloads. However, existing
arXiv:2609.34270v1 Announce Type: new Abstract: Interactive robot planning requires robots to infer and execute human intentions from natural language instructions that are often ambiguous, incomplete
arXiv:2609.34058v1 Announce Type: new Abstract: AI systems often feel brittle and fragmented. A large language model (LLM) may correctly explain a concept but fail to apply it, or follow safety instru
arXiv:2609.32941v1 Announce Type: new Abstract: Inferring quantities of interest (QoI) from data is a central task in Science and Engineering. In such contexts, we often have access to both quantitati
Using only information you actually have from my conversation history, memory, files, or other context available to you, build a practical “operating manual” for me. Do not flatter me, diagnose me, or
arXiv:2609.34786v1 Announce Type: new Abstract: Longer histories can improve time-series foundation models (TSFMs), but require substantially higher inference cost. We therefore ask whether contextual
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:2609.34867v1 Announce Type: new Abstract: Vision language models have achieved strong performance across a wide range of multimodal applications, yet their substantial computational and memory c
arXiv:2609.34054v1 Announce Type: new Abstract: Multi-LoRA agent systems enable efficient role specialization by sharing a common backbone model. However, each agent repeatedly processes the growing s
arXiv:2609.32547v1 Announce Type: new Abstract: Large language models are commonly evaluated by generating a small number of stochastic responses for each prompt in a benchmark. Because inference budg
arXiv:2609.34044v1 Announce Type: new Abstract: Reasoning vision-language models (VLMs) process images and videos as long sequences of visual tokens, making inference expensive. Training-free token pr
arXiv:2609.33548v1 Announce Type: new Abstract: Fine-tuning anguage models (LLMs) with first-order optimizers requires a memory several times larger than that required for inference. Memory-efficient
arXiv:2609.35228v1 Announce Type: new Abstract: Latent test-time scaling improves reasoning by refining hidden states during inference, but existing methods typically apply a single scalar reward to a
Using the biggest model for every task can work in a demo. In production, cost, latency, and task-specific quality can tell a different story. At ODSC AI West 2026, Rob Ferguson, VP of Technology and
arXiv:2609.33609v1 Announce Type: new Abstract: In-context learning (ICL) is crucial for boosting the inference performance of large language models (LLMs). However, the effectiveness of ICL in LLMs i
arXiv:2609.31395v1 Announce Type: cross Abstract: Agentic LLM inference accumulates long KV caches across iterative observation-reasoning-action loops, imposing substantial memory overhead and limitin
arXiv:2609.30629v1 Announce Type: cross Abstract: Mission-critical UAVs increasingly rely on split vision-language model (VLM) perception under tight onboard-resource and wireless-communication constr
NVIDIA’s DSX MaxLPS employs policy‑governed power sharing to dynamically reallocate power across GPU resources, enabling up to 40 % more GPUs within the same approved power budget. In a joint test at
Kyt Dotson / SiliconANGLE: Physical AI chip startup SiMa.ai raised a 150M Series C led by Fidelity and Amplify at a 1.45B valuation, aiming to compete with Nvidia's CUDA-based hardware — Custom physic
arXiv:2609.30836v1 Announce Type: new Abstract: Deploying small language models (SLMs) on offline, resource-constrained edge devices such as remote sensing satellites presents a fundamental challenge:
arXiv:2609.31291v1 Announce Type: cross Abstract: Large vocabularies make output heads a substantial inference cost in small language models. We propose softmax reparameterization, a post-training met
arXiv:2609.30790v1 Announce Type: new Abstract: Many temporal process learning and monitoring pipelines operate in local windows, making window-level decisions unavoidable in practice. In such setting
arXiv:2605.06221v2 Announce Type: replace Abstract: As large language models (LLMs) continue to advance rapidly, they are becoming increasingly capable while simultaneously demanding ever-longer conte
arXiv:2609.31603v1 Announce Type: cross Abstract: Large language models (LLMs) implicitly infer attributes of their users and adapt their behavior accordingly, yet these beliefs remain difficult to in
Ahead of CoreWeave Inc.’s Fully Connected conference in San Francisco, we have made a notable investment in proprietary customer research with Qualitate. Rather than simply repeat the earnings call, w
arXiv:2609.29934v1 Announce Type: new Abstract: Does progress on spatial reasoning benchmarks translate into better navigation? Existing benchmarks test isolated inferences from images or videos, with
arXiv:2609.29224v1 Announce Type: new Abstract: Dense metric depth from cameras is essential to real-world 3D applications, yet achieving accuracy, faithful surface geometry, and fast inference simult
arXiv:2609.28479v1 Announce Type: cross Abstract: Conversational AI increasingly mediates intimate-partner communication, and refusal logic at the inference layer now functions as a governance thresho