Knowledge catalogue
arXiv:2606.05181v1 Announce Type: new Abstract: Natural Language Inference (NLI) is a fundamental task in natural language understanding that requires determining the logical relationship between a pr
arXiv:2606.05308v1 Announce Type: cross Abstract: With PRECISE, we extended Prediction-Powered Inference to produce bias-corrected estimates of ranking evaluation metrics by combining a small human-la
arXiv:2606.04581v1 Announce Type: cross Abstract: Speculative inference (SPIN) was originally developed as an efficient architecture to accelerate Large Language Models (LLMs). In this work, we propos
arXiv:2606.04511v1 Announce Type: new Abstract: Sparse attention reduces compute and memory bandwidth for long-context LLM inference. However, two key challenges remain: (1) KV cache capacity still gr
Together AI provides the inference stack behind both: high-throughput serving on the latest NVIDIA Blackwell GPUs for agentic workloads, and TensorRT engines plus event-driven streaming I/O for low-la
Day 2 at #MSBuild is about what it takes to move beyond generic foundation models. Think customization, inference performance, and getting production-ready AI deployed at scale. @chahvivi will lead a
arXiv:2606.02955v1 Announce Type: cross Abstract: Diffusion large language models promise parallel token generation, yet inference remains bottlenecked by deciding which masked tokens can be safely co
Fine-tuning to production inference is the gap where teams get stuck. At #MSBuild today, our own Rob Ferguson, @danielhanchen (@UnslothAI) and @marksaroufim (@coreautoai) discuss: model customization
arXiv:2606.02981v1 Announce Type: new Abstract: Best-of-N inference scaling (drawing N candidate answers from a language model and returning the one a reward model ranks highest) improves accuracy by
arXiv:2606.03026v1 Announce Type: cross Abstract: Spiking language models expose activation sparsity that dense Transformer runtimes do not directly exploit. This paper studies that property from a sy
arXiv:2606.03358v1 Announce Type: new Abstract: Smart meter data can reveal sensitive socio-demographic characteristics of households, raising privacy concerns. While this risk has been demonstrated a
Using open models and inference clouds (which serve open models) is a leading indicator of what is to come. The advantage of open weights is that you can train, serve, and continually improve your own
arXiv:2606.00618v1 Announce Type: new Abstract: Generative models have emerged as a powerful paradigm for AI planning, yet their performance remains constrained by the training data distribution. One
arXiv:2603.12037v2 Announce Type: replace Abstract: Foundation models based on prior-data fitted networks (PFNs) have shown strong empirical performance in causal inference by framing the task as an i
arXiv:2511.01064v3 Announce Type: replace-cross Abstract: Variational inference (VI) approximates a target density p by the best match q in a family of tractable distributions. The best variational ap
arXiv:2606.01273v1 Announce Type: new Abstract: Spatio-temporal point processes (STPPs) provide a principled framework for modeling asynchronous events in continuous time and space. Recent diffusion-b
arXiv:2512.06906v2 Announce Type: replace-cross Abstract: Detecting the anomalies of web applications, important infrastructures for running modern companies and governments, is crucial for providing
Move from test to production by running high-performance inference directly on Foundry. At #MSBuild, we demoed an end-to-end workflow showing how unified infrastructure improves latency, reduces cost,
arXiv:2606.02430v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly integrated into high-performance computing (HPC) workflows, accelerating scientific discovery through di
arXiv:2606.01923v1 Announce Type: new Abstract: Large Language Models (LLMs) frequently exhibit 'contextual disregard' when faced with input evidence that conflicts with their internal parametric memo
arXiv:2606.00739v1 Announce Type: new Abstract: Large language models hallucinate even when the answer lies within their parameters. While inference-time scaling can surface this latent knowledge, the
MiniMax-M3 is a large language model capable of handling 1 million token contexts and multimodal inputs while maintaining efficient inference performance. Together AI's blog post discusses techniques
arXiv:2606.00516v1 Announce Type: new Abstract: Mixed batching (MB)--interleaving prefill and decode in a single batch--has become the standard scheduling strategy for large language model (LLM) infer
Today we're announcing that hybrid agentic inference is coming to Perplexity Computer. Computer can split tasks between a local model running on your machine and frontier models in the cloud. This kee
arXiv:2506.22666v3 Announce Type: replace-cross Abstract: The rise of API-only access to state-of-the-art LLMs highlights the need for effective black-box jailbreak methods to identify model vulnerabi
arXiv:2605.31352v1 Announce Type: new Abstract: Robotics manipulation usually assumes that the shape and pose of the object are known to the robot prior to motion planning. However, precise geometric
arXiv:2605.30571v1 Announce Type: cross Abstract: Physical AI systems, including robots, autonomous vehicles, embodied agents and edge copilots, often run a different inference workload from cloud LLM
MiniMax M3 is live and Together AI is powering its inference 🚀 Tomorrow at 6pm PT we're going live on X Spaces with the teams behind the model and the infrastructure to give you a deep dive. https://x
arXiv:2605.30991v1 Announce Type: cross Abstract: Inference-time reward alignment steers pretrained diffusion and flow-based generative models to satisfy user-specified rewards without retraining. Rec
what a wonderful project: parakeet.cpp https://github.com/mudler/parakeet.cpp GGML based parakeet inference pipeline that's 2x faster than my ONNX parakeet pipeline on Apple Silicon! (Needed a few loc
arXiv:2605.29454v1 Announce Type: new Abstract: While Membership Inference Attacks (MIAs) are the prevailing method for identifying training data, their application has expanded into privacy auditing
arXiv:2601.14855v3 Announce Type: replace Abstract: Black-box variational inference (BBVI) with Gaussian mixture families offers a flexible approach for approximating complex posterior distributions w
arXiv:2605.29233v1 Announce Type: cross Abstract: Diffusion language models (dLLMs) generate text by iteratively denoising multiple token positions in parallel, offering an attractive alternative to s
Having Grok Build sub-agents to iterate several ideas for me on data loading, batching, inference, and writing results to files for dense datasets before I went to sleep. It gave me a nice summary of
arXiv:2605.30218v1 Announce Type: new Abstract: Temperature-zero BF16 LLM inference is often treated as reproducible, yet the same request can emit different tokens when decoded alone or inside a larg
The Information: Sources: ByteDance has partnered with chipmaker InnoStar to develop an AI inference chip modeled after Groq's LPUs, which are built to run AI models at low cost — TikTok owner ByteDan
arXiv:2605.30253v1 Announce Type: cross Abstract: We study the contraction in Wasserstein distance of the coordinate ascent variational inference algorithm. This is shown to hold under a transport-inf
arXiv:2605.28792v1 Announce Type: new Abstract: Electroencephalography (EEG) is a critical, non-invasive method to monitor electrical brain activity. EEGs can span anywhere from a couple seconds to mu
arXiv:2605.27428v1 Announce Type: new Abstract: Edge deployments of generative inference increasingly face two practical realities: per-device per-model performance is often unknown at deployment time
Every LLM API call depends on the inference engine underneath it. Tokenization, scheduling, prefill, decode, KV cache, batching, and streaming determine whether the experience is fast, scalable, and p
arXiv:2603.20980v2 Announce Type: replace-cross Abstract: Time-varying causal models provide a powerful framework for studying dynamic scientific systems, yet most existing approaches assume that the
glad to know Mythos' safety concerns have been addressed right as Anthropic also secured tens of billions in inference compute 👍 JUST IN: Anthropic announces it will roll out Claude Mythos “in the com
Elon Musk indicated that the next development phase involves implementing an inference stack in C (with some C++) to enable high-speed reinforcement learning operations simultaneously across a large c
arXiv:2512.09786v2 Announce Type: replace Abstract: Examples of embedded intelligence include a wide variety of tiny neural networks used on-board wireless sensors and actuators, which are expected to
arXiv:2512.11280v2 Announce Type: replace Abstract: Large language models (LLMs) have achieved remarkable performance across a wide range of tasks, but their increasing parameter sizes significantly s
arXiv:2602.15919v2 Announce Type: replace-cross Abstract: Recent work in the privacy literature shows that sample-targeted membership inference attacks (MIAs) significantly outperform untargeted appro
arXiv:2605.27130v1 Announce Type: cross Abstract: We present DEI: Diversity in Evolutionary Inference, a distributed Quality-Diversity (QD) search framework that assigns heterogeneous large language m
i own 0 A100s but i can run cloud inference with sub 80ms network latency by renting one in Kansas (0% action queue starvation) this is an early checkpoint of smolvla trained on 50 episodes for ~20k s
arXiv:2510.08932v2 Announce Type: replace Abstract: Recently, a growing body of research has focused on either optimizing CTR model architectures to better model feature interactions or refining train
arXiv:2605.26546v1 Announce Type: new Abstract: Mobile graphical user interface (GUI) agents enable AI models to autonomously operate smartphones on behalf of users. However, most existing systems foc
Super happy that a bunch of people are finding marlin useful. Thank you for the inference support @ZeroGPU_AI @huggingface 🥰🤝 We’ve got hands on more compute now so we’ll also release a series of blog
Train with autoregression & convert weights to diffusion for inference. Most researchers agree that autoregression is best when memory bandwidth is cheap and diffusion is best when FLOPS are cheap. Th
arXiv:2605.25230v1 Announce Type: new Abstract: Recent work on recursive architectures has shown that tiny neural networks can be surprisingly powerful on structured reasoning tasks. The trick is to m
arXiv:2511.16449v4 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have shown great potential for embodied AI by integrating visual perception, language understanding, and a
arXiv:2510.02361v2 Announce Type: replace-cross Abstract: Transformer-based large models excel in natural language processing and computer vision, but face severe computational inefficiencies due to t
arXiv:2605.24799v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong capabilities across a wide range of vision language tasks. However, when applied to
arXiv:2605.24172v1 Announce Type: new Abstract: Secure patient-provider messages contain clinically important communication behaviors that are difficult to characterize manually at scale. The Electron
arXiv:2602.00491v2 Announce Type: replace Abstract: Public health reasoning requires population level inference grounded in scientific evidence, expert consensus, and safety constraints. However, it r
arXiv:2605.24168v1 Announce Type: new Abstract: Sparsity has long been a central theme in LLM efficiency, but its role in context processing remains unresolved. As LLM workloads shift toward longer co
arXiv:2605.25244v1 Announce Type: new Abstract: Inference time optimization techniques, such as repeated sampling, have significantly advanced the reasoning capabilities of Large Language Models (LLMs