Search: “inference”

arXiv:2608.28405v1 Announce Type: new Abstract: Current cultural evaluations for large language models (LLMs) often reduce culture to single-turn factual recall via MCQs, failing to capture a common u

arXiv:2608.27633v1 Announce Type: new Abstract: Pothole detection and its severity measurement is still an important challenges in urban infrastructure management, where late maintenance directly cont

Excited to welcome @greptile, the AI code reviewer trusted by 11,000+ teams, as a Together AI customer. Greptile's agents review and test pull requests with full context of your codebase, and running

Enterprise experimentation with cloud AI has run into a wall of data-control, sovereignty and token-cost questions, pushing intelligence back toward infrastructure enterprises own. The result is a reb

arXiv:2608.28361v1 Announce Type: cross Abstract: Machine Unlearning methods for Large Language Models typically assume pre-specified forget and retain sets. In realistic settings, however, requests m

Great paper from Google and colleagues. It proposes an interesting approach to improve agents on long-horizon tasks. Long-running agents slow down and start poisoning their own context. Both symptoms

arXiv:2608.27985v1 Announce Type: new Abstract: Monte Carlo Tree Search (MCTS) and every-visit Monte Carlo (MC) control are usually presented as different methods. MCTS is described in the language of

arXiv:2603.17070v2 Announce Type: replace Abstract: In this work, we analyze shortcomings in cross-lingual knowledge transfer in large, modern reasoning LLMs. We demonstrate that the perceived gap in

arXiv:2608.28460v1 Announce Type: new Abstract: Autoregressive video diffusion enables scalable long-video generation by producing chunks from a bounded recent context. While recency-based caching pre

arXiv:2608.27756v1 Announce Type: new Abstract: Determining whether large language models derive answers from context or prior knowledge remains a fundamental challenge. Self-contained linguistic olym

arXiv:2608.28375v1 Announce Type: cross Abstract: Global goodness-of-fit and discrepancy statistics can establish that a sample departs from a reference distribution without identifying which observat

arXiv:2608.27899v1 Announce Type: new Abstract: With the growing prevalence of large language model (LLM) generated content, watermarking is considered a promising approach for attributing text to LLM

arXiv:2608.27466v1 Announce Type: new Abstract: Web content extraction is essential for reliable LLM data pipelines, yet existing methods often struggle to jointly satisfy accuracy, scalability, and a

arXiv:2608.28198v1 Announce Type: new Abstract: Privacy-preserving learning is often motivated by the idea that protecting users' data can preserve trust and thus participation, improving utility in t

arXiv:2608.28256v1 Announce Type: cross Abstract: Deep generative models have recently emerged as powerful priors for solving ill-posed inverse problems in CT, with diffusion-based approaches achievin

arXiv:2608.28075v1 Announce Type: new Abstract: Manipulation in partially observable environments requires planning under incomplete scene information. In such settings, an initially valid plan may ex

arXiv:2511.17721v2 Announce Type: replace-cross Abstract: Data assimilation is a fundamental task in updating forecasting models upon observing new data, with applications ranging from weather predict

arXiv:2608.27584v1 Announce Type: new Abstract: Autonomous systems rely on extracting information from light, yet remain brittle in extreme environments, from nighttime navigation to high-speed roboti

arXiv:2510.17252v2 Announce Type: replace Abstract: News media can influence readers not only through the events they report but also through the emotional tone used to present them. This issue is esp

Mac Studio, 96GB unified memory (M3 Ultra). I want the largest usable Qwen3.8-Flash-Next setup, and I'd rather not burn 100GB of bandwidth on the wrong download. Here's my math. Please tell me which p

TL;DR: Ninfer/DS4 but for RDNA4 Highly custom kernels built for RDNA4, applied to vLLM-Radiance to greatly improve Qwen3.8 Flash Next speeds. This is mostly for dual R9700s with preferably 48GB of RAM

arXiv:2608.28366v1 Announce Type: cross Abstract: State estimation in magnetohydrodynamic flows is critical for real-time monitoring of liquid metal blankets in tokamak fusion reactors. Due to the mul

arXiv:2603.21366v2 Announce Type: replace Abstract: Autoregressive video diffusion has recently emerged as a promising paradigm for long-video generation, enabling causal synthesis beyond the temporal

arXiv:2608.27529v1 Announce Type: new Abstract: Streaming 3D reconstruction from extremely long videos requires estimating camera motion and scene geometry online under bounded memory and computation.

arXiv:2608.27704v1 Announce Type: new Abstract: When machine learning classifiers are retrained, inputs correctly classified by the previous model version may be misclassified by the updated version,

arXiv:2608.27461v1 Announce Type: new Abstract: Relational reasoning requires the process of perceptual understanding, comparing, and integrating the underlying relationships between concepts. This ab

arXiv:2608.28383v1 Announce Type: cross Abstract: Hybrid attention dominates frontier LLMs, yet Vision Transformers (ViTs) in multimodal LLMs lack a satisfactory hybrid design, with no consensus on wh

arXiv:2608.27462v1 Announce Type: new Abstract: Unlike explicit attacks with obvious profanity, implicit hate speech hides malice within seemingly compliant expressions through metaphors and contextua

Interesting new paper from Alexia Jolicoeur-Martineau (of Tiny Recursive Model fame) and collaborators. They seem to be able to replace quadratic attention with sliding window attention + attention si

Sori-1B is a 1B-parameter audio-language model built by a single SNU researcher whose core claim to fame is that its decoder is trained entirely from scratch on audio-paired text — no text-only pretra

arXiv:2606.20543v2 Announce Type: replace Abstract: Autoregressive image models treat images as 1D token sequences, inheriting the next-token factorization of language models. This flattening discards

arXiv:2608.27948v1 Announce Type: new Abstract: Test-time adaptation (TTA) on graphs aims to adapt a graph neural network (GNN) that is well-trained on the training graph to the test graph, which invo

arXiv:2608.27871v1 Announce Type: new Abstract: Long-video understanding remains challenging for Multimodal Large Language Models (MLLMs) due to limited context length. Uniform sampling may miss cruci

arXiv:2608.27931v1 Announce Type: new Abstract: This study proposes a novel framework to estimate parameters for reproducing target multicellular patterns using an agent-based model (ABM). Two major c

arXiv:2608.28138v1 Announce Type: new Abstract: Adapting video vision-language models (VLMs) is computationally expensive because video inputs produce a large number of visual tokens, making both fine

arXiv:2608.27514v1 Announce Type: new Abstract: Diffusion-based language models (dLLMs) enable parallel token generation through iterative denoising, but existing decoding strategies collapse to singl

arXiv:2603.20111v2 Announce Type: replace Abstract: The Joint-Embedding Predictive Architecture (JEPA) is often seen as a non-generative alternative to likelihood-based self-supervised learning, empha

arXiv:2608.27562v1 Announce Type: new Abstract: Translating continuous, noisy egocentric video streams into discrete, temporally ordered action steps is fraught with visual challenges. Heavy ego-motio

arXiv:2608.28216v1 Announce Type: new Abstract: Locating a specific object instance in a cluttered scene using a single reference image and a short description, and reporting when that instance is abs

Together AI, in partnership with greptile, announces its AI‑powered code‑review platform that is trusted by more than 11,000 teams for reviewing pull requests within the full context of their codebase

11/ METR and Redwood’s work is extremely valuable, but it assesses model behavior and alignment. That is only half the picture. We also need an independent account of how OpenAI’s containment failed.

This has been a big 2 weeks for local models with 3.8 27B and Next coming out, a lot of 'frontier labs are done' comments which, in general, could certainly be true. Could be trillions in economic val

TL;DR: Every public low-bit GGUF of this model is secretly ~4.70 bpw. Shim the rows to 256 and it becomes a real 3.07 bpw / 11.77 GiB file that runs 262K context on 16GB. Needs patched llama.cpp — not

One time, a young ML researcher asked Master Ilya: 'Teacher, according to the formulas, if I use the same seed and same prompt with the same weights, I will get the same results. Is my math right?' Ma

I wanted to share my successful setup for running a Qwen 3.8 27B model with a massive context window on a consumer 16GB GPU (RTX 4070 Ti SUPER). The goal was to fit everything into VRAM without sacrif

arXiv:2601.21217v2 Announce Type: replace-cross Abstract: We introduce a flexible empirical Bayes approach for fitting Bayesian generalized linear models. Specifically, we adopt a novel mean-field var