Knowledge catalogue
arXiv:2603.06642v2 Announce Type: replace-cross Abstract: Test-Time Training (TTT) language models replace the KV-cache with fast weights updated during inference, achieving O(1) memory but suffering
arXiv:2607.20558v1 Announce Type: cross Abstract: AI Assistants are increasingly deployed in high-stakes settings, such as healthcare or government services. Yet their real-world behavior remains poor
arXiv:2501.18897v4 Announce Type: replace-cross Abstract: Generative models have achieved remarkable success across a range of applications, yet their evaluation still lacks principled uncertainty qua
arXiv:2510.24616v4 Announce Type: replace-cross Abstract: For four decades statistical physics has been providing a framework to analyse neural networks. A long-standing question remained on its capac
Statistics of week: “More Americans pay for sports betting apps (5%) than pay for AI… 37% of consumers say none of AI's uses are helpful. … 2.2% penetration nearly four years after ChatGPT launched. N
Stay hungry, stay foolish. Absolute legend For my first post, I’m sharing a letter @NVIDIA signed on why open models matter. AI will transform every industry, power every company, and be built by ever
arXiv:2607.20592v1 Announce Type: new Abstract: Spatio-temporal machine-learning modelling is an important tool in environmental research. However, machine-learning models are highly sensitive to both
arXiv:2607.20464v1 Announce Type: new Abstract: When a language model gives different answers on repeated runs, does that variation reveal what it does not know? Self-consistency turns the variation i
arXiv:2607.21239v1 Announce Type: new Abstract: Polarization cues benefit applications such as material detection and de-reflection, yet acquiring them typically requires dedicated hardware. This moti
arXiv:2607.21594v1 Announce Type: new Abstract: Multi-agent interactive world models should not only generate consistent observations, but also maintain world states that persist across agents and evo
arXiv:2607.20545v1 Announce Type: new Abstract: Diffusion models have become competitive generators for time series, but their practical use is limited by the large number of sequential denoising step
arXiv:2511.00418v2 Announce Type: replace Abstract: Physics-Informed Neural Networks (PINNs) offer a flexible framework for solving nonlinear partial differential equations (PDEs), yet conventional im
arXiv:2509.14257v3 Announce Type: replace-cross Abstract: Large Language Model agents achieve strong performance on multi-step reasoning and tool-use tasks, but their impressive capabilities typically
arXiv:2607.20813v1 Announce Type: new Abstract: Pixel-aligned Gaussian splatting enables efficient and generalizable novel-view synthesis. However, high-resolution rendering faces a critical trade-off
arXiv:2512.17951v3 Announce Type: replace Abstract: Recent progress in flow-based generative models and reinforcement learning (RL) has improved text-image alignment and visual quality. However, curre
arXiv:2607.21574v1 Announce Type: new Abstract: Surprisal theory holds that the human processing difficulty of a linguistic unit in context is an affine function of its surprisal under some language m
https://huggingface.co/swiss-ai/Apertus-v1.5-70B https://huggingface.co/swiss-ai/Apertus-v1.5-8B Apertus 1.5 is a family of 8B and 70B parameter language models designed to advance the state of multil
The rapid evolution of intelligent software-defined systems is pushing chip design into a new era of physical AI, one where chip design complexity is outpacing traditional engineering methods. Manufac
arXiv:2607.21577v1 Announce Type: cross Abstract: Quality control in printing, particularly in rotogravure printing, still depends on slow, costly, and subjective manual inspection. Automated surface
arXiv:2607.20787v1 Announce Type: cross Abstract: For two decades, the standard remedy for class-imbalanced learning has been to fabricate synthetic minority examples, and the standard evidence of the
arXiv:2607.21228v1 Announce Type: new Abstract: Structured understanding of satellite video is essential for advancing dynamic geospatial scene analysis from low-level perception to high-level cogniti
arXiv:2607.21017v1 Announce Type: new Abstract: The development of generalizable robotic manipulation policies is inherently bounded by the availability of large-scale, high-fidelity scene data. While
arXiv:2607.11007v2 Announce Type: replace Abstract: Few-shot multimodal classification commonly attaches a lightweight head, such as k-nearest neighbors, logistic regression, or a linear SVM, to a fro
arXiv:2506.02897v3 Announce Type: replace Abstract: Federated Learning (FL) enables privacy-preserving collaborative model training, but its effectiveness is often limited by client data heterogeneity
arXiv:2511.05385v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) utilizes external knowledge to augment Large Language Models' (LLMs) reliability. For flexibility, agenti
arXiv:2607.20510v1 Announce Type: new Abstract: We introduce Telco-GAIA, a bilingual, multi-modal benchmark for evaluating tool-using agents on the data of a real-world telecommunications operator. Te
arXiv:2607.20911v1 Announce Type: new Abstract: We introduce Tencent WorkBuddy Bench, a multi-domain evaluation suite for coding agents; this report documents its construction methodology, scoring pro
arXiv:2607.21453v1 Announce Type: new Abstract: Scaling inference-time computation has emerged as a reliable method to improve the performance of large language models on complex reasoning and program
arXiv:2607.21504v1 Announce Type: new Abstract: Numerous 3D assets are discarded due to low texture resolution, while current super-resolution models ignore texture maps and focus on natural images. A
arXiv:2607.20447v1 Announce Type: new Abstract: This paper describes our system for the EEUCA 2026 Shared Task on toxicity classification in gaming chat. We implement a three-stage pipeline combining
arXiv:2607.20512v1 Announce Type: cross Abstract: The Muon optimizer reaches the grokking threshold on modular arithmetic faster than AdamW. Prior work attributes this to 'spectral-norm constraints pl
arXiv:2607.21547v1 Announce Type: new Abstract: The rapid progress of AI has intensified the long-standing pursuit of automation: replacing human participation with algorithms wherever possible. Impli
arXiv:2607.21273v1 Announce Type: new Abstract: Dense per-step supervision is an appealing remedy for sparse-reward, long-horizon LLM agents: reward the agent for predicting its next observation, and
The demand for GLM-5.2 and other frontier-level open models has been surging on Ollama's cloud. We're adding capacity in anticipation for some very large models next week! To make sure Ollama's infras
arXiv:2607.20484v1 Announce Type: new Abstract: Large Language Models (LLMs) are fundamentally limited by representation collapse, a bottleneck that severely degrades long-context performance. We iden
Even if China was distilling from US models (assuming all accusations are true), nothing about it makes it illegal. It is like saying you distilled knowledge from your professor in colleges and now he
arXiv:2607.20803v1 Announce Type: cross Abstract: Activation steering enables control and interpretation of LLMs, yet existing work primarily models personality through static trait frameworks such as
The GPT-5.x Pro series has remained the best models for hard technical problems since they launched. There is some parallel model magic going on that is not well-explained. Anthropic has never had an
arXiv:2607.11149v3 Announce Type: replace Abstract: LLM agent benchmarks measure task completion, reliability, and inference cost, but not the persistent data an agent run leaves on disk, including lo
arXiv:2607.20781v1 Announce Type: new Abstract: Artificial Intelligence (AI) is rapidly transforming organizations, raising a fundamental organizational and economic question: when will a human employ
The knowledge that makes AI useful is diffused. It lives with scientists, engineers, clinicians, firms. For AI to benefit from distributed knowledge, it must itself be distributed. Agree with Jensen t
arXiv:2607.18652v2 Announce Type: replace-cross Abstract: We establish a widetildeOmega(d^{5/4}sqrt T) lower bound on the minimax expected regret of stochastic bandit convex optimization of 1-Lipschit
arXiv:2607.21078v1 Announce Type: new Abstract: Single-Image Defocus Deblurring (SIDD) aims to recover an all-in-focus image from a single defocused observation, but rigorous and reproducible evaluati
arXiv:2607.21118v1 Announce Type: new Abstract: This paper presents a review of the second LoViF Challenge on Real-World All-in-One Image Restoration. The challenge aims to advance unified image resto
arXiv:2607.20449v1 Announce Type: cross Abstract: LLMs are trained predominantly on human-authored text, yet the structural and narrative conventions embedded in that text are rarely examined as a sou
The Washington Post processed 1.79B input tokens per month through Together AI, running open models like Llama and Mistral in production with predictable costs and full control over the model stack. T
arXiv:2607.20952v1 Announce Type: cross Abstract: Latent, or silent, reasoning lets language models carry out intermediate computation in continuous vector space instead of words, and is widely assume
arXiv:2607.20552v1 Announce Type: new Abstract: Grokking -- the delayed generalization of neural networks long after they have memorized their training data -- wastes thousands of training epochs and
arXiv:2607.21468v1 Announce Type: cross Abstract: People often use handwritten notes and sketches to externalize ideas for ideation. To integrate large language models (LLMs) into this practice, we pr
This has my full support. Jensen is right. For my first post, I’m sharing a letter @NVIDIA signed on why open models matter. AI will transform every industry, power every company, and be built by ever
This is a big jump in ARC-AGI-3. Claude Opus 5 from @AnthropicAI is the new SOTA on ARC-AGI-3: 30.2% The previous high score (7.8%) was set by GPT-5.6 Sol (Max) Throughout our analysis, we observed no
arXiv:2607.20459v1 Announce Type: cross Abstract: Multi-hop question answering requires retrieving and integrating evidence from multiple contexts. Despite the rapid progress of current research, mult
arXiv:2607.20914v1 Announce Type: new Abstract: Federated parameter-efficient fine-tuning (PEFT) enables communication-efficient adaptation of large pretrained models on decentralized edge data, but i
arXiv:2510.14854v4 Announce Type: cross Abstract: Magnetic induction (MI) communication (MIC) has emerged as a promising candidate for underground communication networks due to its excellent penetrati
arXiv:2607.21433v1 Announce Type: cross Abstract: Chain-of-thought reasoning models such as DeepSeek-R1-Distill-Qwen-7B exhibit a bimodal convergence pattern: generations either terminate within a tok
arXiv:2501.19337v5 Announce Type: replace Abstract: A name alone measurably reshapes a language model's next-token distribution before a single token is sampled. We measure full-vocabulary Shannon ent
arXiv:2607.20437v1 Announce Type: new Abstract: Production Retrieval Augmented Generation (RAG) systems rely on aggregating multiple external documents to answer complex queries. However, the retrieve
arXiv:2602.19313v2 Announce Type: replace-cross Abstract: General-purpose robot learning requires dense, instruction-conditioned feedback that can distinguish meaningful task progress from stalled, fa
arXiv:2510.11147v2 Announce Type: replace-cross Abstract: This paper introduces torchsom, an open-source Python library that provides a reference implementation of the Self-Organizing Map (SOM) in PyT
arXiv:2607.21111v1 Announce Type: cross Abstract: Offline Reinforcement Learning (RL) agents are trained on fixed behavioral trajectories, which makes trajectory-level deletion important when selected