127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “inference”

20,505 results

Model Releases

Neural Transport Nested Sampling

DGX agent

arXiv:2609.29413v1 Announce Type: new Abstract: Sampling from Boltzmann distributions of molecular systems is an inference problem that has seen significant recent developments fuelled by advances in

model-releasesarxiv-cs-lg

25 Sept 2026

Research

Search: “inference”

Neural Transport Nested Sampling

OncoVision: Integrating Mammography and Clinical Data through Attention-Driven Multimodal AI for Enhanced Breast Cancer Diagnosis

TabSieve: Explicit In-Table Evidence Selection for Tabular Prediction

The Tokens Remember: When Tokenization Bypasses Knowledge Editing and Unlearning

Thinking Leakage: A Causal Audit of NoThink Post-Training in Hybrid Reasoning Models

When Can Agents Forget Their Reasoning? ICLR for Long-Horizon Agent Context Compression

BiCFlow-MER: Orchestrating Discriminative and Generative Multimodal Emotion Recognition via Conditional Transport

CereVLA: Cerebellum-Inspired Consequence-Aware Residual Governance for Efficient Vision-Language-Action Execution

I built a presentation generator that works with Ollama — would love some feedback

Inverse Problems Conditioned on Observation Ensembles: Applications and Methods

KITE: KV-Invariant Transformer Expansion for Efficient Agentic LLM Scaling

Qwen3.8-Flash-Next on 12GB VRAM - 65 tokens per second

Recursive Uncertainty-Gated Image Registration for Learning-based Algorithms

Resource-Adaptive Stochastic Gradient Descent for Online Linear Programming without Re-solving

Rolling Conformal Prediction in Sequential Model Training

SkillGym: Internalizing Human Skills into LLMs for Real-World Problem Solving

Stable Geometry with Divergent Task Evidence for Efficient Long-Horizon Agent Compression

CODA: Depth-Aligned Scene Completion and Object Decomposition from a Single RGB-D Image

CoEvo: Oracle-Grounded Self-Evolution of a Single Model for Multi-Step Causal Reasoning

DVA-Neurons: Design and Verification of Adaptive LIF Neurons: From Single-Neuron Dynamics to Multi-Neuron Spiking Networks

Few-Shot Demonstrations Elicit the Use of In-Context World Representations in LLMs

How SWE-Serve Exposes the Gap Between Local Tests and Live Serving

On Basis Function Selection for Sparse Gaussian Process Regression

Recursive self-improvement of AI research agents

SPECTRA: Adaptive Execution of Speculative Decoding on a Runtime-Reconfigurable Tiled Architecture

STAR-VAE: A Scalable Latent-Variable Transformer for Controllable Molecular Generation

When Recursive Models Finish Computing

When Scaling Fails: Mitigating Audio Perception Decay of LALMs via Multi-Step Perception-Aware Reasoning

A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents

Acceptance-Aware Draft Model Training for Speculative Decoding

AdaMem: Adaptive Memory Token Allocation for Soft Compression in Retrieval-Augmented Generation

AgentRouter: Heterogeneous Model Routing for Cost-Optimal Multi-Step Agentic Workflows

Algebraic Consistency Alone Does Not Certify Temporal Structure in Latent Action Models

Applications of Neural Cellular Automata: State of the Art, Challenges and Opportunities

Authorship identification under domain shift: a survey of stylistic measures and learned author representations

Beyond Raw Context Transfer: Representation-based Federated Retrieval-Augmented Generation

Block-Sparse Attention with Semantic-Geometric Decoupled Routing

Calibrating Lightweight Sparse Autoencoder Feature Steering

Causal Bayesian Optimization: Foundations, Methods, and Applications

Correlation-Aware Structured Pruning for Large Language Models

COT-TTS: Audio Context-Aware Text-to-Speech with Chain-of-Thought Reasoning

Custom Named Entity Recognition and Topic Classification for Global Health Publications

Fast Graph Laplacian Estimation using Effective Resistance

FoldQuantVLA: Native Low-Bit Quantization of Vision-Language-Action Models via Consistent Folding

H-Spec: Parallel Speculative Decoding Without a Drafter-Side KV Cache

Introducing DigitalOcean Managed Agents: One AI-native stack to power your intelligence

Measured Joules, Learned Routes: Learning to Route for Energy-Efficient LLM Serving

MIRA: Real-Time Full-Duplex Human-Robot Interaction for Embodied Companions