127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “inference”

20,509 results

Safety

Belief-Aware VLM Model for Human-like Reasoning

DGX agent

arXiv:2604.09686v1 Announce Type: new Abstract: Traditional neural network models for intent inference rely heavily on observable states and struggle to generalize across diverse tasks and dynamic env

safetyarxiv-cs-ai

14 Apr 2026

Research

Beyond Theory of Mind in Robotics

DGX agent

arXiv:2604.09612v1 Announce Type: new Abstract: Theory of Mind, the capacity to explain and predict behavior by inferring hidden mental states, has become the dominant paradigm for social interaction

Search: “inference”

Belief-Aware VLM Model for Human-like Reasoning

Beyond Theory of Mind in Robotics

Characterizing Performance-Energy Trade-offs of Large Language Models in Multi-Request Workflows

MeloTune: On-Device Arousal Learning and Peer-to-Peer Mood Coupling for Proactive Music Curation

NameBERT: Scaling Name-Based Nationality Classification with LLM-Augmented Open Academic Data

SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding

StyleBench: Evaluating thinking styles in Large Language Models

b8771

Bayesian Social Deduction with Graph-Informed Language Models

Reservoir observer enhanced with residual calibration and attention mechanism

Run it on the AI Native Cloud — serverless and dedicated infrastructure. https://www.together.ai/models/minimax-m2-7

DIVERSED: Relaxed Speculative Decoding via Dynamic Ensemble Verification

Dual-Pool Token-Budget Routing for Cost-Efficient and Reliable LLM Serving

From Exposure to Internalization: Dual-Stream Calibration for In-context Clinical Reasoning

HAWK: Head Importance-Aware Visual Token Pruning in Multimodal Models

$S^3$: Stratified Scaling Search for Test-Time in Diffusion Language Models

Foundry Local is now Generally Available

How to Accelerate Protein Structure Prediction at Proteome-Scale

Amortizing Sequential Experimental Design in Reasoning LLMs

BASIS: Evaluating Belief-Aware Solutions in Interactive Settings beyond Instructions

BiShield-TEE: On the (In-)Security of Unilateral Weight Obfuscation in On-Device TEE-Shielded LLM Partition

FALCON: FPGA-Accelerated Latency-Certifiable Occupancy Networks for Camera-Based Autonomous Driving

Large Language Models Naively Recover Ethnicity from Individual Records

Learn Only Where You Can't Compute: Structured Corrections to Gaussian Process Posteriors

RecSoup: Efficient Model Merging Approach for Controllable Multi-Objective Recommendation

ShiftQAT: Quantization-Aware Training for the Numerical Contract of a Fixed-Function Edge CNN Accelerator

Value-Informed Schedule Trimming for Accelerated Sequential Monte Carlo Guidance in Discrete Diffusion

CHEAR: Confusion-Hierarchy Evidence-Aware Reasoning for Cost-Efficient Human Activity Recognition

Complementary Future Token Pruning for World Action Models

Diff Diffusion: Predicting Edit Paths with Diffusion Models for Efficient Code Editing

Empowering Edge Agents: A Systematic Analysis of Edge-Cloud Collaboration in LLM Agent Execution

FleetPilot: Fine-Grained Steering Empowers Real-World LLM Personalization

Genesis Steering: Better Activation Steering Through Training Data

How Visko streams real-time world models on Google Cloud TPUs

Refine Actions If Needed: Adaptive Action Chunk Refinement for Robot Manipulation

Reliable Text-to-SQL in Resource-Constrained Settings with Small LLMs via Iterative Retry Workflows

Spectral-MoE: Heterogeneous Per-Layer Expert Utilization in Dense-to-MoE Conversion

STP-GUI: Spatially-Aware Token Pruning for Efficient Web-GUI Agents

Adaptive-Depth Is a Finishing Stage

Dynamic Interpolation for Training-Time Prediction Reshaping in Low-Light Image Enhancement

Elephant in the Fridge: Constant-Memory Frame Packing for Long Video Understanding

Error-Based Bidirectional Predictive Coding Enables Deep, 4-Bit Predictive Coding Networks

Fast Quantized Johnson-Lindenstrauss Transforms

I trained a 15M 'decision-only' model two ways — linear recurrence vs Transformer attention. Accuracy was a coin flip; latency and training cost weren't.[R]

Joint Neural Posterior Estimation and Model Selection for Chemical Reaction Networks

Linear-Time Non-Local Codec Placement for Machine Learning Model Compression

MARS: Systematic Multi-Level Acceleration for World Action Models

MERIT: Scaling KG Foundation Models with Relation Transformers