Search: “models”

arXiv:2610.12048v1 Announce Type: new Abstract: Deep neural networks, including large language models, have achieved remarkable performance across various tasks. However, they are prone to overconfide

arXiv:2610.10626v1 Announce Type: new Abstract: Neural surrogates for vector-valued partial differential equations can fit training data yet change their predictions when the same physical state is ex

arXiv:2610.11389v1 Announce Type: new Abstract: Neural Machine Translation (NMT) models, while capable of producing highly fluent outputs, remain vulnerable to hallucinations, which are translations t

arXiv:2610.11310v1 Announce Type: new Abstract: While 3D spatial reasoning in dynamic egocentric environments is crucial for embodied intelligence, audio-visual large language models (AV-LLMs) lack ex

arXiv:2610.11472v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning often improves language-model performance by giving models additional computation before answering. However, explicit C

arXiv:2610.11918v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) increasingly incorporate explainable reasoning for emotion understanding. However, reasoning based mai

arXiv:2510.00536v2 Announce Type: replace Abstract: Graphical user interface (GUI) agents built on vision-language models have emerged as a promising approach to automate human-computer workflows. How

arXiv:2610.10633v1 Announce Type: cross Abstract: Screening in systematic reviews (SRs) is manual and time-consuming. Prior work has explored large language models (LLMs) for automating this step, but

I built MaRN (Mapping Networks), a PyTorch library that lets you optimize a compact latent representation instead of directly training every model parameter. Some results from my current benchmarks: M

arXiv:2610.12310v1 Announce Type: new Abstract: A single multimodal large language model (MLLM) struggles to excel simultaneously at detection, localization, description, and reasoning in multimodal i

arXiv:2610.11538v1 Announce Type: cross Abstract: Deep randomized models fix hidden-layer parameters through random initialization and learn only closed-form readouts, typically adding depth by stacki

LM Studio 0.4.26 is out now! • ⚡️ `/v1/systemone` and `/v1/decisions` APIs • 👾 Coexistence with Bionic • 🎨 UI updates and bug fixes Yes, you can now point your Bionic agent to models loaded in your LM

arXiv:2610.11312v1 Announce Type: new Abstract: Large-scale construction of medical vision-language model (VLM) benchmarks is increasingly feasible with richly annotated imaging datasets and large lan

arXiv:2610.11732v1 Announce Type: new Abstract: Large language model (LLM) agents for portfolio management learn from experience: they credit each experience in their memory with the outcome of the de

arXiv:2610.11628v1 Announce Type: cross Abstract: Machine unlearning updates a trained model after records are deleted, aiming to match exact retraining without repeating the full training procedure.

arXiv:2610.10909v1 Announce Type: cross Abstract: Membership inference attacks (MIAs) threaten the privacy of machine learning (ML) training data by determining whether a sample was used to train a ta

arXiv:2610.12423v1 Announce Type: new Abstract: We present Pumpire, a unified benchmark for evaluating metric point-pair distance estimation capability of both image- and video-level 3D foundation mod

(Don't judge by the screenshot, the cache is cold. It hits 24+ tok/s with a warm cache!) About two months ago, I made a post here asking whether predicting which MoE experts would be used on the next

arXiv:2610.11004v1 Announce Type: cross Abstract: Reconstructing spatially resolved plasma dynamics from few sensors is essential for diagnostics, reduced-order modelling and control, yet remains diff

arXiv:2610.11775v1 Announce Type: new Abstract: Sparse Mixture of Experts (MoE) models scale more efficiently than dense models by routing tokens to modular expert networks that are only active for pr

arXiv:2610.11552v1 Announce Type: new Abstract: Large language model agents can invoke tools fluently, but enterprise workflows demand more than selecting the right tools: actions must strictly comply

arXiv:2610.10624v1 Announce Type: cross Abstract: Spatial audio-visual understanding requires models to recognize not only what is present, but also where events occur and how they relate across modal

arXiv:2610.11567v1 Announce Type: cross Abstract: Battery state of health (SoH) forecasting is important for battery management, but remains challenging due to nonlinear degradation and heterogeneity

arXiv:2610.10929v1 Announce Type: cross Abstract: Speculative decoding is a popular technique for increasing the speed and reducing the costs of large language model (LLM) inference by verifying multi

I tested Mellum2.1-12B-A2.5B (Q8) locally using Pi and llama-server. All five tests were one-shot. Results were pretty mixed: - Pelican SVG, Browser OS, Minecraft: Poor results. - Bouncing Hexagon: Ph

arXiv:2610.11216v1 Announce Type: cross Abstract: Diffusion and autoregression (AR) have long been seen as different categories of generative models, with diffusion specialising in continuous fields a

arXiv:2610.10639v1 Announce Type: cross Abstract: Visible Chain-of-Thought (CoT) is often treated as a broadly useful reasoning instruction, yet analytics code generation combines natural-language amb

1/ My heart is heavy. I made a number of mistakes in my life, and not asking earlier for an immediate slowdown is one of them. If OpenAI starts making similar breakthroughs in biology, we risk somethi

arXiv:2603.06655v2 Announce Type: replace Abstract: We introduce FCBNet, an efficient model designed for camouflaged weed detection. The architecture is based on a fully frozen ConvNeXt backbone, the

arXiv:2610.09003v1 Announce Type: new Abstract: Autoregressive Large Language Models (LLMs) frequently struggle with deterministic multi-step algorithmic tasks such as multi-digit multiplication and l

Anthropic: Anthropic launches OSS Scanner, a free opt-in vulnerability scanner for critical open-source projects; its AI-generated reports are sent without human review — We're launching OSS Scanner,

arXiv:2505.21468v2 Announce Type: replace Abstract: We present Causal Posterior Estimation (CPE), a novel method for Bayesian inference in simulator models, where evaluating the likelihood function is

arXiv:2610.09541v1 Announce Type: cross Abstract: Signals that predict whether a chain-of-thought (CoT) trace is correct are compared by AUC, but deploying one requires a threshold with a guarantee. W

arXiv:2610.09587v1 Announce Type: cross Abstract: Reasoning capabilities are critical for advancing Large Language Models, yet current approaches either require massive computational budgets or strugg

arXiv:2610.09221v1 Announce Type: cross Abstract: Flow and diffusion models suffer from slow inference due to computationally expensive numerical integration. Distillation provides a promising way for

arXiv:2610.10536v1 Announce Type: cross Abstract: Modern language models undergo reinforcement learning with verifiable rewards (RLVR) on top of already-trained checkpoints. A key promise of RLVR is t

arXiv:2610.09821v1 Announce Type: new Abstract: Generative 3D Gaussian head avatars provide high-quality, efficient rendering, but synthesising the Gaussian representation remains computationally expe

arXiv:2610.09919v1 Announce Type: new Abstract: Hessian spectra at trained models in deep learning exhibit a persistent pattern: eigenvalues organize into distinct clusters, including a large bulk nea

arXiv:2609.35308v2 Announce Type: replace Abstract: Large language models treat conversation history as unverified context, so false premises injected into prior turns can be adopted as fact, a failur

arXiv:2610.08882v1 Announce Type: cross Abstract: FinVector-Market-4B adapts Qwen/Qwen3.5-4B with rank-16 LoRA on a 22,000-example corpus for structured financial tasks. We evaluate the base and adapt

arXiv:2610.08959v1 Announce Type: new Abstract: On-policy distillation post-trains large language model agents by supplying dense, step-level guidance from a teacher policy when the reinforcement-lear

arXiv:2610.09624v1 Announce Type: cross Abstract: Tool calling, invoking external tools on demand, is central to agentic LLMs, yet the mechanism that decides whether a model calls a tool or responds d

arXiv:2607.18130v2 Announce Type: replace Abstract: Finetuning methods for foundation models usually change weights, prompts, or hidden states, while leaving the residual topology fixed. We ask whethe

arXiv:2610.10318v1 Announce Type: new Abstract: Social media is a rich source of real-time public sentiment, but widely used sentiment analysis tools are often applied without understanding their limi

Here is the story: Nvidia has published this work (with source code available) called dreamDojo which is a world model for robotics based of their prior work Cosmos 2.5 which is cited about 100 times

arXiv:2610.10276v1 Announce Type: cross Abstract: An LLM safety patch can pass a benchmark while still being a poor repair. This risk is especially acute for jailbreak repairs, where the goal is to co