Knowledge catalogue
arXiv:2610.00411v1 Announce Type: new Abstract: Contemporary Genomic Foundation Models (GFMs) rely on a DNA-as-a-string paradigm that employs masked token prediction objectives for pretraining. Howeve
arXiv:2610.00666v1 Announce Type: cross Abstract: Qualitative comparison figures are central evidence in computer vision papers, and vision-language models (VLMs) are increasingly used to judge them.
arXiv:2610.00713v1 Announce Type: new Abstract: When a graph neural network (GNN) explainer produces an unexpected attribution on a molecule, the attribution alone cannot reveal whether the explainer
arXiv:2609.38342v1 Announce Type: new Abstract: On-policy self-distillation uses a model as its own teacher to provide dense supervision for reasoning, often through reference-solution conditioning. P
arXiv:2609.38645v1 Announce Type: cross Abstract: Models are usually aligned based on their observed outputs, using demonstrations, preference data, or reward signals. These objectives reward response
arXiv:2609.39394v1 Announce Type: new Abstract: Large language models often solve independent problems in the same conversation. Can computation from earlier problems help them solve new ones? To answ
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:2609.38356v1 Announce Type: new Abstract: Dynamical Systems Reconstruction (DSR) aims to infer models from observed time series that reproduce a system's qualitative long-term behavior. Continua
arXiv:2609.38879v1 Announce Type: cross Abstract: Large language models rely heavily on human text, which often conveys surface answers rather than the spatial and structural logic behind them. Protei
arXiv:2609.38335v1 Announce Type: cross Abstract: Coding agents powered by large language models (LLMs) are evolving from making localized code changes to developing complete software repositories. Ho
arXiv:2609.39786v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly combined with knowledge graphs (KGs) to ground reasoning in structured evidence. However, most LLM-based K
I've run the benchmark on a RTX 3090, 1024 tokens in / 256 out, concurrency 1–32. If the model fits on vRAM (Gemma-4-26B-A4B, byte-identical GGUF on both engines): llama.cpp has 2.2–3.2× the throughpu
So everyone has been yelling about how I should be using Gufo instead of halogen because it's open source and it's 'just as good or better'. Checking in on their GitHub (GitHub.com/gufo-org/gufo) got
arXiv:2609.39137v1 Announce Type: new Abstract: Scaling Large Language Models (LLMs) via Mixture-of-Experts (MoE) enables massive parameter growth with nearly constant per-token computation. However,
arXiv:2609.40335v1 Announce Type: new Abstract: Differentially Private Stochastic Gradient Descent (DP-SGD) is a leading approach for privacy-preserving fine-tuning of large language models (LLMs). Ma
arXiv:2609.39527v1 Announce Type: new Abstract: The presence of lens flares in images can significantly reduce the quality of downstream application results for tasks such as 3D scene reconstruction.
arXiv:2609.39185v1 Announce Type: new Abstract: Mamba-style and hybrid language models compress their past into a fixed-size recurrent state that is rewritten at every generated token. Storing this st
arXiv:2609.39147v1 Announce Type: new Abstract: Current image-to-video models achieve visual realism and physical plausibility, but reasoning about mental states remains unexplored. Actions are driven
arXiv:2609.39324v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have recently incorporated world models to provide richer dynamic supervision beyond sparse action labels. However
arXiv:2609.39076v1 Announce Type: new Abstract: A pool of language models can collaborate and improve collectively by learning from one another's responses. These interactions depend on the instructio
arXiv:2609.40108v1 Announce Type: new Abstract: Opioid overdose remains a major clinical and public health burden, highlighting the need for scalable approaches to identify patients at high risk. Here
arXiv:2609.38458v1 Announce Type: new Abstract: Clinical large language model (LLM) agents deployed locally can consult more capable remote models, but doing so risks exposing patient information. Pri
arXiv:2602.06924v3 Announce Type: replace Abstract: Deep learning models trained to optimize average accuracy often exhibit systematic failures on particular subpopulations. In real-world settings lik
arXiv:2609.40359v1 Announce Type: new Abstract: We find that major reported improvements in decoding words from non-invasive brain recordings are largely reproducible without any brain data. In the in
arXiv:2609.38526v1 Announce Type: cross Abstract: Scaling laws for optimization against reward models in AI alignment have pinned down how performance depends on optimization effort---measured by a KL
arXiv:2609.40316v1 Announce Type: cross Abstract: Looped transformers and Mixture-of-Experts (MoE) offer complementary routes to efficient scaling: recurrence increases computational depth at fixed pa
arXiv:2609.38899v1 Announce Type: cross Abstract: Video Multimodal Large Language Models (Video-MLLMs) support reasoning over video inputs, yet remain vulnerable to jailbreak attacks that elicit polic
arXiv:2609.38600v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly used in clinical settings, it is critical to evaluate their reliability under realistic variation in cl
arXiv:2602.14049v2 Announce Type: replace-cross Abstract: Spatio-temporal traffic forecasting is a core component of intelligent transportation systems, supporting various downstream tasks such as sig
arXiv:2609.38621v1 Announce Type: new Abstract: Two scientific findings can disagree without contradicting each other. Determining whether they conflict requires knowing whether they describe comparab
arXiv:2609.39325v1 Announce Type: new Abstract: The ability of Large Language Model (LLM) agents to complete daily and professional work is receiving increasing attention. Training such agents require
arXiv:2609.38142v1 Announce Type: new Abstract: A small trainable advisor can steer a frozen language-model executor using natural-language advice. In addition to learning from task rewards, the advis
arXiv:2609.37993v1 Announce Type: cross Abstract: The BITEM team entered both subtasks of the NTCIR-19 R2C2 task with a single agentic pipeline, in which a model searches, reads and records evidence o
Breakthroughs on every frontier. I can't wait to share more on what Praxis-1 will unlock across industries. Media Introducing Praxis-1, an open-weight World Action Model that turns our video pre-train
arXiv:2609.37841v1 Announce Type: new Abstract: Masked generative models offer parallel token prediction, but accurate parallel sampling must account for dependencies among tokens. When dependencies a
arXiv:2609.36570v1 Announce Type: cross Abstract: Indirect prompt injection makes an LLM agent treat untrusted retrieved text as instructions. We present CounterSteer, an inference-time defense that s
arXiv:2609.38165v1 Announce Type: new Abstract: The landscape of satellite imagery time series datasets and boundary-pushing architectures for cropland segmentation has never been richer. However, in
arXiv:2609.35879v1 Announce Type: cross Abstract: Benchmarks for large language models (LLMs) typically evaluate the accuracy of answers against fixed reference labels. But a central step in many comp
arXiv:2609.38108v1 Announce Type: new Abstract: Large language models (LLMs) enable agents to solve long-horizon tasks by generating a plan and then executing it in an environment. However, successful
arXiv:2609.36849v1 Announce Type: cross Abstract: Safety-aligned language models are commonly deployed as multi-turn assistants, which lets adversaries spread unsafe intent across several user turns i
arXiv:2609.37848v1 Announce Type: new Abstract: Biomedical machine learning papers often compress model performance into one headline number. That number can look like a property of the model even whe
arXiv:2609.37033v1 Announce Type: new Abstract: Federated parameter-efficient fine-tuning enables clients to adapt pre-trained models without sharing raw data or communicating the full model, but stat
Follow-up to my post from about two weeks ago. A lot has changed since then, so I wanted to post an update on where the backend is now. Where the green architectures stand When I posted last time, 7 a
Half a million downloads in a month. Today, our open source family takes another step forward. Thank you for the incredible support behind our first-generation models. We’re excited to introduce TwIL-
I built Image Studio, a local web app for Qwen-Image 2.1 on Apple Silicon. I had the model running on my Mac, but the only way to use it was the ComfyUI graph, and chaining edits meant wiring loaders,
arXiv:2609.36996v1 Announce Type: new Abstract: Knowledge Graph Embedding models have been extensively used to learn representations of entities and relations in Knowledge Graphs for predicting missin
arXiv:2609.37187v1 Announce Type: new Abstract: Language-guided navigation requires connecting partial observations to a persistent spatial reference and learning how actions change that representatio
arXiv:2609.33142v2 Announce Type: replace Abstract: Generating a correct answer does not mean that a language model will select it. We separate factual recall into three steps: generating a correct ca
arXiv:2609.37426v1 Announce Type: cross Abstract: Modern vision-language models (VLMs) have shown promising results in long-video understanding due to the rich semantic information they can capture. H
arXiv:2609.36144v1 Announce Type: new Abstract: Electronic health records provide irregular observations of latent patient states that evolve continuously over time. Recent autoregressive models condi
arXiv:2609.36039v1 Announce Type: cross Abstract: Machine learning (ML) and deep learning (DL) have dominated Intrusion Detection System (IDS) research in recent years. Unfortunately, many existing st
arXiv:2609.36374v1 Announce Type: new Abstract: Feed-forward 3D reconstruction models have achieved impressive performance by scaling model and dataset size, but their cost excludes most research grou
arXiv:2609.38180v1 Announce Type: new Abstract: Existing 3D part decomposition methods do not necessarily partition the original shape into non-overlapping parts that collectively cover the entire sha
I think most people are sleeping on this inference engine. I tried multiple llama.cpp forks and none of them comes close to the inference speed of Strata. Initial version had some bugs with kv cache,
arXiv:2609.36329v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) determines not only how many parameters are trained, but also which local directions a model can move in, so simi
arXiv:2609.37469v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) grounds large language models in external sources, but retrieved passages often name the right entities without pro
arXiv:2609.37402v1 Announce Type: new Abstract: Large language model (LLM) routing reduces serving cost by assigning each query to an appropriate model while preserving response quality. Learning such
arXiv:2609.37294v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for software engineering tasks, yet their stochastic behavior challenges the validity, reproducibil
arXiv:2609.36862v1 Announce Type: cross Abstract: Fine-tuning-as-a-service lets users adapt a safety-aligned language model to their own data, but it also creates a harmful fine-tuning attack surface:
arXiv:2609.36691v1 Announce Type: new Abstract: Manipulation behaviors vary widely across objects and scenes, but they share a small set of reusable skills, and planning with these skills helps embodi