Introducing Three New Serverless Inference Providers: Hyperbolic, Nebius AI Studio, and Novita 🔥

Welcome to Inference Providers on the Hub 🔥

Accelerated Inference with Optimum and Transformers Pipelines

OpenAI o1-mini

Advancing cost-efficient reasoning

Enhancing Small Language Models Reasoning through Knowledge Graph Grounding

arXiv:2607. 14149v1 Announce Type: new Abstract: Although large language models (LLMs) have set benchmarks for zero-shot reasoning, their deployment remains cost-prohibitive and environmentally taxing.

Pre-Compiled Pipeline Shards for Distributed LLM Inference on Intel AI PC Fleets

The paper presents a method for distributing large language model inference across multiple Intel AI PCs by splitting the model into pipeline shards, each pre‑compiled into an OpenVINO graph. Three key techniques—beam_idx Gather to enable GPU optimizations, speculative decoding on stateful models, and interleaved micro‑batching—allow a two‑node Llama 3.1 8B INT4 pipeline to serve two users at 1.79× the throughput of a single‑node model, while a four‑node deployment can run a 70B model that no single PC can hold. The authors provide code, benchmark logs, and reproduction scripts on GitHub.

SciR: A Controllable Benchmark for Scientific Reasoning in LLMs

arXiv:2606. 13020v1 Announce Type: new Abstract: Three paradigmatic forms of inference recur across scientific reasoning: deduction, induction, and causal abduction.

Neuro-symbolic learning over OWL 2 DL via consequence-based compilation to differentiable circuits

arXiv:2608. 17741v1 Announce Type: new Abstract: OWL 2 DL ontologies, grounded in the description logic $\mathcal{SROIQ}$, express large knowledge bases in biomedicine and the Semantic Web.

DeepSWIP: Quotient-WMC Counterfactuals for Neural Probabilistic Logic Programs

arXiv:2606. 20526v1 Announce Type: new Abstract: Neurosymbolic systems such as DeepProbLog combine neural perception with probabilistic logic, but standard inference is associational.

You Only Pass Once: Answering and Abstaining Together in a Single Forward Pass of a Frozen Language Model

arXiv:2608. 14465v1 Announce Type: cross Abstract: A frozen language model on reasoning tasks has two coupled weaknesses: it under-uses evidence its own residual stream already encodes, and it fails to detect when the input is insufficient to answer, so it confabulates.

VERITAS: Verifier-Guided Proof Search for Zero-Shot Formal Theorem Proving

arXiv:2606. 19399v1 Announce Type: cross Abstract: LLM-based formal provers often collapse rich verifier signals (syntax errors, type mismatches, partial goal progress) into a binary pass/fail bit.

SorryDB: Can AI Provers Complete Real-World Lean Theorems?

arXiv:2603. 02668v2 Announce Type: replace Abstract: We present SorryDB, a dynamically-updating benchmark of open Lean tasks drawn from 78 real world formalization projects on GitHub.

DABStep: Data Agent Benchmark for Multi-step Reasoning