Knowledge catalogue
Enterprises are adopting an agentic AI PC strategy as Copilot+ PCs shift AI workloads from expensive cloud inference to secure, high-performance on-device processing. As agentic AI moves from experime
arXiv:2605.26485v1 Announce Type: cross Abstract: We introduce OmniInteract, a streaming benchmark for real-time omnimodal large language models evaluated through native online inference over audio-vi
arXiv:2605.26322v1 Announce Type: new Abstract: Theory of Mind (ToM), the ability to infer others' knowledge, intentions, and emotions, is commonly evaluated in large language models (LLMs) using end-
arXiv:2605.27255v1 Announce Type: cross Abstract: Long chain-of-thought reasoning has made autoregressive decoding the dominant inference cost of modern large language models. Existing methods target
Reachy Mini, a robotic system, can now operate with fully local processing capabilities, enabling on-device inference without requiring cloud connectivity. This advancement allows the robot to run AI
arXiv:2510.04533v2 Announce Type: replace Abstract: Diffusion models achieve state-of-the-art image generation but often produce semantic inconsistencies, or hallucinations. Existing inference-time gu
Tensormesh Inc. has hit upon a way to make artificial intelligence inference more efficient by eliminating the need for redundant computations, and its technology is so convincing that several of AI i
arXiv:2605.27220v1 Announce Type: new Abstract: In modern RAG pipelines, query augmentation methods such as HyDE and query expansion are applied to every query, resulting in substantial LLM inference
arXiv:2605.26660v1 Announce Type: new Abstract: Quantization is an effective approach to reduce the memory footprint and inference cost of large language models (LLMs), yet maintaining performance in
arXiv:2605.24304v1 Announce Type: cross Abstract: Articulated object reconstruction from sparse-view images is an ill-posed problem that requires simultaneous inference of geometry and underlying arti
B9320 is a release of llama.cpp, a C/C++ implementation for enabling LLM inference with minimal setup and state-of-the-art performance on a wide range of hardware locally and in the cloud. The project
arXiv:2605.24793v1 Announce Type: new Abstract: Speculative decoding (SPD) accelerates large language model (LLM) inference by letting a smaller draft model propose multiple future tokens that are ver
arXiv:2510.26418v4 Announce Type: replace Abstract: Large Reasoning Models (LRMs) improve task performance through extended inference-time reasoning. Although previous studies suggest that longer reas
arXiv:2310.04981v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) transform environment percepts into vision-language semantics interpretable by LLMs. However, completing complex
arXiv:2605.24786v1 Announce Type: cross Abstract: Long-horizon LLM inference turns the key--value (KV) cache into the dominant GPU memory consumer and makes per-token attention increasingly expensive.
arXiv:2605.24693v1 Announce Type: new Abstract: Large language models still struggle with contest-level programming, while many agentic remedies rely on massive inference-time sampling or expensive mu
arXiv:2605.25393v1 Announce Type: new Abstract: Large Language Models (LLMs) and Multimodal LLMs (MLLMs) have demonstrated immense potential in autonomous driving (AD) by offering human-like reasoning
arXiv:2602.03983v3 Announce Type: replace Abstract: Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for generalist robotic control. Built upon vision-language model (
arXiv:2605.25645v1 Announce Type: cross Abstract: We present the first end-to-end demonstration of fine-tuning and serving Google's Gemma 4 31B model on TPU hardware, providing an empirical comparison
arXiv:2605.24064v1 Announce Type: cross Abstract: Hyper-relational knowledge graphs (HKGs) effectively represent complex facts. While inferring new knowledge in HKGs is a critical problem, current met
arXiv:2602.01576v2 Announce Type: replace-cross Abstract: Mobile Graphical User Interface (GUI) World Models (WMs) offer a promising path for improving mobile GUI agent performance at train- and infer
arXiv:2605.25811v1 Announce Type: cross Abstract: We study counterfactual distribution learning for high-dimensional outcomes whose counterfactual law may concentrate near lower-dimensional structure.
arXiv:2509.22299v3 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) architectures in large language models (LLMs) deliver exceptional performance and reduced inference costs compared to
arXiv:2605.25967v1 Announce Type: new Abstract: As policy catches up with the capabilities of generative AI, watermarking is central to content provenance efforts. Inference-time watermarks for autore
arXiv:2605.24041v1 Announce Type: cross Abstract: Neural operators serve as fast, data-driven surrogates for scientific modeling but typically rely on a monolithic, single-pass inference procedure tha
arXiv:2605.24647v1 Announce Type: new Abstract: Personalized dialogue requires more than recalling explicit user histories: systems also need to infer hidden user states that evolve through interactio
arXiv:2605.25581v1 Announce Type: new Abstract: Single-cell perturbation prediction aims to infer how cells respond to unseen interventions and to achieve out-of-distribution (OOD) generalization, pro
arXiv:2605.25179v1 Announce Type: new Abstract: Audio-language models (ALMs) are increasingly used for audio captioning, question answering, and open-ended audio understanding, but their inference cos
arXiv:2605.24785v1 Announce Type: new Abstract: Recent advances in multimodal web agents often rely on increased inference-time computation, including rollout search, verifier passes, offline skill di
arXiv:2602.07518v2 Announce Type: replace-cross Abstract: Kolmogorov-Arnold Networks (KANs) shift neural computation from linear layers to learnable nonlinear edge functions, but implementing these no
arXiv:2512.23995v2 Announce Type: replace-cross Abstract: Mixture-of-Experts architectures have become the standard for scaling large language models due to their superior parameter efficiency. To acc
arXiv:2605.24016v1 Announce Type: cross Abstract: Diffusion inference remains costly for edge deployment, yet existing accelerators focus almost exclusively on score networks because standard drift is
arXiv:2605.25745v1 Announce Type: new Abstract: Explicit chain-of-thought (CoT) reasoning substantially improves the reasoning ability of large language models (LLMs), but incurs high inference cost d
arXiv:2605.24433v1 Announce Type: cross Abstract: Flow-matching robot policies commonly use action-chunking inference for efficient closed-loop control, but chunk boundaries can introduce discontinuou
arXiv:2605.26014v1 Announce Type: cross Abstract: Many video reasoning tasks require tracking motion, temporal order, and evolving visual states across frames. Existing methods built on large vision-l
arXiv:2605.25488v1 Announce Type: cross Abstract: Audio-driven talking-head generation has achieved remarkable progress with recent models such as AniTalker, FLOAT, and Sonic. Despite their success, m
arXiv:2605.23918v1 Announce Type: cross Abstract: The AI inference industry keeps models loaded in GPU memory around the clock to avoid cold-start latency, implicitly treating idle power as a fixed co
Hugging Face has released 1-bit and Ternary Bonsai Image 4B, a new family of lightweight image-generation models optimized for efficient diffusion inference. These models are designed to deliver high-
arXiv:2605.25133v1 Announce Type: new Abstract: Reliably knowing when a language model is correct is almost as important as being correct. We introduce prover-verifier deliberation (PVD), an inference
arXiv:2605.25566v1 Announce Type: new Abstract: Clinical decision-making requires reasoning over incomplete, imprecise, and linguistically expressed patient narratives. While large language models (LL
arXiv:2605.24202v1 Announce Type: new Abstract: Multi-agent LLM workflows route inference through specialized roles to lift end-task accuracy, but jointly training those roles with reinforcement learn
arXiv:2605.23258v1 Announce Type: new Abstract: KV cache growth is a major bottleneck for long-context inference in large language models. Existing methods are often dominated by binary eviction or re
arXiv:2605.23200v1 Announce Type: cross Abstract: The linear growth of the Key-Value (KV) cache is a critical bottleneck in long-form LLM inference. Existing KV compression methods mitigate this by ev
As enterprises confront spiraling cloud inference bills, on-prem AI computing is emerging as the decisive lever for making agentic AI economically viable at scale. Dell Technologies Inc.’s announcemen
arXiv:2510.09450v2 Announce Type: replace Abstract: Low-light video enhancement (LLVE) is challenging due to noise, low contrast, and color degradation. While learning-based methods enable fast infere
arXiv:2605.23096v1 Announce Type: cross Abstract: Fully homomorphic encryption (FHE) enables private inference by evaluating neural networks on encrypted data. In this way, we can delegate the computa
This post discusses how OpenAI is burning 17 billion annually despite 20+ billion in revenue because unit economics for AI inference are fundamentally broken, with the company losing more money on que
arXiv:2605.23652v1 Announce Type: new Abstract: On a 300-persona life-simulation benchmark, pcsp achieves compositional zero-shot persona identification up to 17x above chance, Spearman rho approx 0.7
OpenStudio is a hybrid AI router that combines local model inference with cloud-based model access through OpenRouter, a unified API providing access to hundreds of AI models through a single endpoint
arXiv:2605.23771v1 Announce Type: cross Abstract: Virtual photography asks an agent to enter a prepared 3D scene with no preselected camera pose or reference image, infer a suitable shot from scene in
arXiv:2605.22984v1 Announce Type: cross Abstract: Test-Time Training (TTT) is an emerging paradigm that enables models to adapt their parameters during inference, improving performance on tasks such a
arXiv:2605.23872v1 Announce Type: new Abstract: We introduce training-free looped transformers, in which a lightweight inference-time wrapper loops a contiguous mid-stack block of layers of a frozen c
arXiv:2605.22717v1 Announce Type: cross Abstract: Interactive streaming music generation promises the use of generative models for live performance and co-creation that is impossible with offline mode
arXiv:2605.21780v1 Announce Type: new Abstract: Randomized smoothing is a powerful tool for certifying robustness to adversarial perturbations, including poisoning attacks via randomized training and
arXiv:2602.01279v2 Announce Type: replace Abstract: Bayesian Last Layers (BLLs) provide a convenient and computationally efficient way to estimate uncertainty in neural networks. However, they underes
RWKV-7 G1g is here: the world's best pure RNN LLM, and a competitive LLM in general. Try https://huggingface.co/spaces/BlinkDL/RWKV-Gradio-2 for bsz16 7B inference. G1h in June 🙂 p.s. const 15000+tps
arXiv:2605.22082v1 Announce Type: new Abstract: We present CoRMA(Contrastive Robotic Motor Adaptation), a context-based meta-adaptation framework that modifies RMA for force-dominant assembly. CoRMA r
arXiv:2605.21964v1 Announce Type: new Abstract: Computational imaging enables compact infrared systems, but deep-learning pipelines that combine image reconstruction and object detection often introdu
arXiv:2605.22147v1 Announce Type: new Abstract: High-resolution remote sensing images (RSIs) are crucial for Earth observation applications, yet acquiring them is often limited by sensor constraints a
arXiv:2605.21661v1 Announce Type: cross Abstract: Adapting pretrained diffusion models to downstream objectives such as inverse problems often requires expensive test-time guidance or optimization. We