All entries

context : autoscale n_ctx_train when yarn scaling specified (#28030) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44499127 macOS/iOS: macOS Apple Silicon

kv-cells: look up the n-gram history in the sequence position index (#28040) get_prev_tokens() rebuilt a (seq, pos) -> token hash map on every ubatch by walking all used cells, while llama_kv_cells al

cuda: fuse MoE weighted expert reduction (#25952) cuda : fuse MoE weighted reduction (mul + view + add) The MoE combine tail currently writes weighted expert outputs to global memory before reducing t

arXiv:2608.29232v1 Announce Type: cross Abstract: Object detectors are typically trained under closed-set supervision, where unlabeled regions are implicitly treated as background. Under incomplete an

arXiv:2608.30724v1 Announce Type: cross Abstract: LLM agents are increasingly used to run autonomous ML experiments, iterating on target metrics with little human oversight. Prior work has documented

arXiv:2608.30044v1 Announce Type: new Abstract: Language models are commonly compared by averaging scores across a benchmark list with equal weight. Such lists grow through publication outside an expl

arXiv:2608.30141v1 Announce Type: cross Abstract: Preference optimization is widely used to align large language models with human preferences, but preference-data composition may also influence priva

Banger paper from the Qwen team. If you evaluate agents on anything longer than a single session, this one is worth your time. (bookmark it) E-Commerce Bench runs an agent through a simulated 365-day

Bank of England governor Andrew Bailey today warned that advanced artificial intelligence poses risks to financial infrastructure. Bailey outlined his concerns in a letter to G20 finance ministers and

arXiv:2608.29196v1 Announce Type: new Abstract: Optic disc (OD) segmentation is essential for diagnosing ophthalmic pathologies from retinal fundus images. However, prevailing deep learning approaches

arXiv:2608.30283v1 Announce Type: cross Abstract: Expected-cost constraints can still permit rare, high-cost events. Monte Carlo conditional value at risk (CVaR) gradients can be noisy at high confide

arXiv:2608.29553v1 Announce Type: new Abstract: Geospatial foundation models such as the AlphaEarth Foundation produce compact and globally consistent representations of the Earth's surface that trans

arXiv:2608.30524v1 Announce Type: cross Abstract: Beamforming methods in millimeter-wave (mmWave) cell-free massive multiple-input multiple-output (CFmMIMO) systems require accurate channel state info

arXiv:2608.30367v1 Announce Type: new Abstract: Transformer-based electrocardiogram (ECG) models commonly tokenize waveforms into fixed temporal patches. Though convenient, fixed patching can split he

arXiv:2608.30536v1 Announce Type: new Abstract: Reliable execution of long-horizon mobile manipulation tasks remains challenging because overall task success depends on the successful completion of mu

arXiv:2608.29428v1 Announce Type: new Abstract: Single-trial EEG analyses are often organized around events and latencies, yet EEG-based reaction-time (RT) prediction is posed as scalar regression on

arXiv:2608.29463v1 Announce Type: cross Abstract: A benchmark score is a joint property of the model, the evaluation harness, the elicitation budget, the sampled population, and contamination status.

arXiv:2608.30418v1 Announce Type: cross Abstract: Resting-state functional magnetic resonance imaging (rs-fMRI) functional connectivity (FC) matrices are widely used for individual-level prediction, b

arXiv:2608.30175v1 Announce Type: new Abstract: Peptide-protein affinity models are often evaluated with a single data split, obscuring whether they interpolate among measurements for observed targets

BenchMIRT is a new method for auditing LLM benchmarks question by question, revealing which capabilities they actually measure and helping researchers build smaller, more focused, and easier-to-interp

arXiv:2608.29206v1 Announce Type: new Abstract: Bias in human-agent interaction can manifest not only through hostile language but also as benevolent bias, whereby unequal treatment hides behind a war

arXiv:2512.03400v2 Announce Type: replace-cross Abstract: We study how explicit world-modeling objectives affect the internal representations and downstream capability of Transformers, using Rubik's C

arXiv:2608.30467v1 Announce Type: new Abstract: Deep-learning models can achieve strong chest X-ray (CXR) classification performance without establishing whether their predictions predominantly rely o

arXiv:2608.30364v1 Announce Type: new Abstract: Retail banking attrition is usually represented as a terminal binary event, even though client relationships often weaken earlier through partial moveme

arXiv:2608.30373v1 Announce Type: new Abstract: Multi-Agent Debate (MAD) has been widely adopted to improve LLM-based evaluation by prompting multiple agents to negotiate and reach a consensus. Howeve

arXiv:2608.29127v1 Announce Type: new Abstract: We propose a scalable, validity-oriented pipeline for evaluating biomedical LLM judges when high-quality human judgments are scarce. First, we augment e

arXiv:2602.01695v2 Announce Type: replace Abstract: Latent reasoning reduces the token-generation cost of chain-of-thought reasoning by replacing explicit intermediate tokens with continuous latent tr

arXiv:2608.29990v1 Announce Type: cross Abstract: Large language models are increasingly deployed in Arabic-speaking markets, yet standard benchmarks overwhelmingly reward Modern Standard Arabic (MSA)

arXiv:2608.29804v1 Announce Type: new Abstract: Virtual try-on (VTON) requires not only realistic generation but also faithful preservation of garment characteristics. However, existing evaluation met

arXiv:2608.30866v1 Announce Type: new Abstract: Building language technologies and conducting NLP research for low-resource languages---particularly when led by native speakers or involving participat

arXiv:2606.16206v2 Announce Type: replace Abstract: Large language models are increasingly proposed as educational tutors, yet stronger task-solving ability does not necessarily imply stronger learnin

arXiv:2606.15932v3 Announce Type: replace Abstract: While Large Language Models (LLMs) have substantially advanced text-to-code generation, many real programming tasks specify intent through visual ar

arXiv:2608.30398v1 Announce Type: new Abstract: In pointwise document reranking, Chain-of-Thought models typically underperform direct scoring models. While existing diagnostics attribute this to infe

arXiv:2608.30333v1 Announce Type: cross Abstract: Next-basket repurchase recommendation is commonly formulated as a ranking task: given a customer's purchase history, the system ranks previously purch

arXiv:2608.28787v1 Announce Type: new Abstract: Joint-embedding predictive architectures (JEPAs) have primarily been developed for self-supervised representation learning. Denoising JEPA (D-JEPA) rece

arXiv:2608.24621v2 Announce Type: replace Abstract: Can language models be trusted in safety- critical operations? In such settings, strong per- formance on semantic metrics does not guaran- tee opera

arXiv:2508.14323v3 Announce Type: replace Abstract: Tool-augmented LLMs invoke external functions to extend their capabilities, but errors in the invocation decision, such as calling a tool when none

arXiv:2603.26737v2 Announce Type: replace-cross Abstract: Current multimodal LLMs encode images as static visual prefixes and rely on text-based reasoning, lacking goal-driven and adaptive visual acce

arXiv:2608.29610v1 Announce Type: new Abstract: The current alignment tuning paradigm for Large Language Models (LLMs) prioritizes surface-level behaviors -- fluency, safety, and tonal consistency. Wh

arXiv:2608.30256v1 Announce Type: cross Abstract: Logical reasoning with large language models (LLMs) is a critical capability, as it reflects a system's ability to correctly deduce hypotheses from a

arXiv:2608.28725v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as graders, verifiers, and process auditors, but most mathematical evaluations still emphasize final-

arXiv:2510.03136v2 Announce Type: replace Abstract: Confidence calibration, the alignment of a model's predicted confidence with its actual accuracy, is crucial for the reliable deployment of Large La

arXiv:2608.30686v1 Announce Type: cross Abstract: Coding agents are increasingly used for software engineering tasks, including bootstrapping projects from third-party repositories whose integrity can

arXiv:2608.30319v1 Announce Type: cross Abstract: Large language models (LLMs) finetuned for specialized domains represent crucial high-impact applications. Inference-time alignment improves safety de

arXiv:2608.30035v1 Announce Type: new Abstract: Self-evolving reasoning frameworks train a Challenger to generate questions exposing a Solver's weaknesses, creating adaptive curricula without human da

arXiv:2608.28699v1 Announce Type: new Abstract: Understanding long-form video remains a fundamental challenge for multimodal large language models (MLLMs). Sparse frame sampling fails to capture fine-