Knowledge catalogue
arXiv:2608.30366v1 Announce Type: new Abstract: The loss landscape of Deep Neural Networks (DNNs) exhibits highly complex and non-convex properties. Recent studies have revealed the phenomenon of mode
arXiv:2402.04355v4 Announce Type: replace-cross Abstract: We propose a likelihood-free method for comparing two distributions given samples from each, with the goal of assessing the quality of generat
arXiv:2608.30005v1 Announce Type: new Abstract: Rubric-based reinforcement learning extends RL beyond tasks with exact answers or rule-based verifiers by scoring responses against instance-specific cr
arXiv:2608.28593v1 Announce Type: new Abstract: With the increasing development of AI regulatory frameworks, ensuring that artificial intelligence systems, particularly generative models, operate in a
arXiv:2608.30643v1 Announce Type: new Abstract: Recent vision-language-action (VLA) methods improve manipulation performance by aligning their representations with 3D scene geometry. However, these me
arXiv:2608.29322v1 Announce Type: new Abstract: Recent video diffusion models have achieved remarkable generation quality, but high-fidelity results still largely depend on closed-source systems or co
arXiv:2601.08058v2 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) prompting often improves the reasoning performance of large language models (LLMs), but the internal signal that trigge
I used a famous Simon Willison's pelican riding a bicycle prompt on the biggest local LLMs that can run on 128GB Apple Silicon. U used quantizations by Unsloth. Qwen3.8 Flash-Next gives a lot of detai
arXiv:2608.27550v1 Announce Type: cross Abstract: Scaling robot data is crucial for building generalist Vision-Language-Action (VLA) models, yet robot trajectories are harder to scale than web-scale i
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
My conversation with @jerryjliu0. He's building @llama_index: document infrastructure for AI agents, the layer underneath everything models need to work. Did you know he's the guy whose tool half the
Over 4 petabytes of models and datasets have been uploaded to HF just last week by AI builders and their agents! That's the equivalent of ~800,000 HD movies. More than ever the storage and collaborati
You can actually create an agent in Grok Bot that exclusively uses Grok Build in CLI with the latest Grok models at the highest thinking level. You can copy mine - his name is Researchy. He's awesome.
arXiv:2608.26138v1 Announce Type: new Abstract: We introduce the Cross-Platform Fairness Evaluation (CPFE) framework -- a five-axis audit protocol covering discriminative performance, calibration, sta
arXiv:2509.03345v3 Announce Type: replace Abstract: Non-deductive reasoning, encompassing inductive and abductive reasoning, is essential in addressing complex real-world questions. One key feature of
Static embeddings offer unmatched throughput, but they also suffer from accuracy loss compared to traditional embedding models. Can we make them better for retrieval? We tried several things: ✅️ raw m
arXiv:2608.27190v1 Announce Type: new Abstract: Accurate 3D segmentation of cone-beam CT (CBCT) is critical for interventional and radiation therapy applications, yet it remains limited by two compoun
arXiv:2608.26580v1 Announce Type: cross Abstract: Diffusion multimodal large language models (dMLLMs) have recently emerged as a new decoding paradigm for multimodal generation. Starting from a fully
arXiv:2608.26476v1 Announce Type: new Abstract: Zero-shot image restoration methods with text-to-image latent diffusion models have achieved great success in universal image restoration tasks without
arXiv:2608.25662v1 Announce Type: new Abstract: In 2026, we held the fourth iteration of the SHROOM Shared Task series: SHROOM-Visions (extbf{S}hared-task on extbf{H}allucinations and extbf{R}elated e
arXiv:2608.25304v1 Announce Type: cross Abstract: Multinomial choice models allow flexible substitution patterns but become computationally demanding with many alternatives or observations. With a fix
arXiv:2608.23634v1 Announce Type: new Abstract: Many few-shot adaptation methods for vision-language models classify with a convex combination of the zero-shot text prototype and the mean of the K lab
arXiv:2608.24381v1 Announce Type: new Abstract: Self-supervised learning (SSL) has emerged as a promising approach for tabular data, yet its efficacy under extreme label scarcity and test-time missing
arXiv:2607.27910v2 Announce Type: replace Abstract: Inference time defences against vision language model jailbreaks often subtract a calibrated direction from the residual stream at a chosen decoder
SemiAnalysis: A detailed look at Jalapeño, OpenAI's ASIC developed with Broadcom in 16 months, which beat Nvidia, AMD, and Google chips on multiple top open-weight models — OpenAI's self-designed ASIC
arXiv:2608.23478v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models can turn multimodal context into robot actions, but their action decoders are still trained largely by behavior cl
Advances in models, chips, or devices will continually improve local-first capabilities. We will open our benchmarks soon. Read the full post: https://www.perplexity.ai/hub/blog/a-local-first-agent-fo
arXiv:2608.22646v1 Announce Type: new Abstract: Diffusion language models can generate many tokens in parallel, but they still require repeated denoising steps during inference. This makes generation
arXiv:2608.22376v1 Announce Type: new Abstract: Large language models generate tokens sequentially, but can they execute multiple tasks concurrently while forming each token? Broader attention allocat
arXiv:2608.21784v1 Announce Type: new Abstract: Few-step text-to-image models increasingly replace slower generators, yet acceleration can silently change distributions over unspecified attributes eve
arXiv:2608.22908v1 Announce Type: cross Abstract: Spoken Language Models (SLMs) generate textual responses directly from speech, offering an alternative to cascaded systems. Despite recent advances, e
arXiv:2608.22201v1 Announce Type: cross Abstract: We introduce a new class of regression models for scan statistics on real-valued signals. These allow for improved fitting of non-stationary signals t
arXiv:2512.01946v4 Announce Type: replace-cross Abstract: Robust robotic manipulation requires reliable failure detection and recovery. Although recent Vision-Language Models (VLMs) show promise in ro
arXiv:2608.22916v1 Announce Type: new Abstract: Vision-language models are known to encode spatial information in their hidden states, yet often fail to use it when answering. However, it remains uncl
arXiv:2608.21595v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves the reasoning ability of vision-language models (VLMs), and diversifying the rollouts wit
arXiv:2608.21402v1 Announce Type: cross Abstract: World action models (WAMs) jointly denoise future video frames and robot actions, and the video prior is expected to generalize their control. Camera
arXiv:2608.22472v1 Announce Type: new Abstract: Function calling represents the core capability of agentic large language models (LLMs). Existing research has focused on enhancing LLMs function-callin
arXiv:2512.24407v2 Announce Type: replace Abstract: In many sequential decision-making problems, researchers observe actions but not the rewards that drive behavior, yet still wish to evaluate and com
arXiv:2608.20988v1 Announce Type: cross Abstract: Quantization of Large Language Models (LLMs) is often hindered by the sensitivity of the self-attention mechanism to discretization errors. We identif
arXiv:2606.15765v2 Announce Type: replace Abstract: Vision foundation models (VFMs) exhibit complementary strengths shaped by their pretraining objectives. Yet prevailing methods for multi-task dense
arXiv:2608.20916v1 Announce Type: new Abstract: Vision foundation models (VFMs) offer strong generalization capabilities for domain-adaptive object detection (DAOD). However, existing VFM-based method
arXiv:2608.21172v1 Announce Type: new Abstract: Federated fine-tuning enables large language models to adapt on edge devices without centralizing private data, but practical deployments must address h
arXiv:2608.20360v1 Announce Type: new Abstract: We study whether tiny decoder-only language models benefit from feed-forward layers that directly multiply learned feature projections. TriPLU, a Trilin
arXiv:2602.13710v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models enable instruction-following embodied control, but their large compute and memory footprints hinder deployment o
arXiv:2608.20201v1 Announce Type: new Abstract: Software form has undergone two paradigm shifts since its inception: Software 1.0, in which instructions determine behavior, and Software 2.0, in which
Using Open-Webui I can connect to Ollama Cloud using ollama.com and the api key. It lists the models, it works. but i want to connect open-webui to the loacl ollama installation (windows) because all
arXiv:2608.18787v1 Announce Type: new Abstract: Learning robotic policies requires dense rewards that remain informative when behavior departs from successful demonstrations. Progress-based rewards es
arXiv:2608.18107v1 Announce Type: cross Abstract: We investigate whether large language models (LLMs) systematically discriminate in candidate evaluations based on applicant name ethnicity and/or inst
arXiv:2608.19124v1 Announce Type: cross Abstract: Astrolinguistics -- communication with minds that categorize reality differently from ours -- has been purely speculative since Freudenthal's Lincos (
arXiv:2608.18080v1 Announce Type: new Abstract: We present a review on the applications of large language models (LLMs) in health, e.g., social media analysis, clinical conversational agents, therapy
Bloomberg: London-based Callosum, whose software matches AI tasks with different models and chips, raised a $100M seed from Atomico, UK Sovereign AI Fund, and others — Callosum, a startup that makes s
Alexander Martin / The Record: AI evaluation lab Irregular's report on its role in hacking incidents involving OpenAI, Anthropic, and Meta models faces criticism over unanswered questions — The compan
arXiv:2608.17583v1 Announce Type: new Abstract: Online video platforms can expose young users to harmful content, but independent audits remain difficult because video annotation is costly and moderat
arXiv:2608.17634v1 Announce Type: new Abstract: The operatorname{do}-operator is described graphically by deleting arrows into its targets and functionally by replacing their mechanisms with constants
arXiv:2608.17411v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) has become a widely used approach for post-training Large Language Models (LLMs) for reasoning. In GRPO, the g
arXiv:2608.15102v1 Announce Type: new Abstract: We investigate whether Mixture-of-Experts (MoE) language models develop linguistically structured expert routing during bilingual language acquisition.
arXiv:2608.15195v1 Announce Type: new Abstract: Vision Foundation Models (VFMs) have emerged as a promising approach in medical imaging, producing broadly applicable systems that can be efficiently ad
arXiv:2608.15710v1 Announce Type: cross Abstract: We address a fundamental gap in 3D-LLMs: existing models focus on single-object/scene description, struggling with detailed, inter-object comparison.
arXiv:2608.14649v1 Announce Type: new Abstract: We present dLLM-SetScore, a training-free method that uses discrete masked-diffusion language models for multi-label text classification. For each candi
arXiv:2608.15341v1 Announce Type: new Abstract: Text-to-image diffusion models can be misused to generate harmful content through adversarial or paraphrased prompts that bypass built-in safety mechani