127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “inference”

20,505 results

Model Releases

Memory Attention

DGX agent

arXiv:2609.28399v1 Announce Type: new Abstract: Language models typically construct attention values from contextual hidden states, even when some of their content may be reusable across contexts. We

model-releasesarxiv-cs-lg

24 Sept 2026

Model Releases

Mizar: A 159M-Parameter Audio-Language Model for Audio Understanding

DGX agent

arXiv:2609.28344v1 Announce Type: cross Abstract: Audio-language models (ALMs) integrate acoustic perception with the knowledge encoded in language models, enabling contextual understanding of auditor

Search: “inference”

Memory Attention

Mizar: A 159M-Parameter Audio-Language Model for Audio Understanding

model : add Ling 3.0 VL support by aetherbird · Pull Request #29151 · ggml-org/llama.cpp

NaviScale: Generating Large-Scale Semantic Map Datasets for Object Navigation

NS-ATTENTION: Newton-Schulz Transformations of Attention Outputs in Vision Transformers

Passing: An Endless Journey through Reconstructed Spacetime with AI-Generated Sound

Pay attention to this new wave of System One models if you are building custom harnesses. First Jev. Now, Contrastive Language Model (CLM). …

PISCES: Physics-Informed Solar-wind Convolutional autoEncoder for Space-weather Anomaly Detection and Early Warning

PR-Smoother: Simulator-Preserving Non-Gaussian Smoothing for Data Assimilation

Proud to be a launch training partner for @LangChain's LangSmith Fine-Tuning and smithtune. LangSmith traces → managed SFT on Fireworks → ev…

Psychoacoustically Aligned Latent Smoothing for Adversarial Robustness of Full-Duplex Speech-to-Speech Dialogue Models

Query Implied Generative Engine Optimization

RAMP: Robust Adaptive Mixed-Precision Quantization for Edge CPU Vision Models

Reflection-Aware Reasoning for Non-Line-of-Sight Pedestrian Localization

Reinforcement Learning with Decomposed Subtasks

Relative Discharge Stage (RDS) Classification: A Practical Indicator of Battery Discharge Progress

Reliable Federated TinyML Deployment for IoT Security

Risk-Controlled KV-Cache Eviction: From Memory Budgets to Risk Targets

Ruby-ASR: Evidence-Preserving Supervision for Joint Orthographic and Lexical-Reading Recognition

Super-Resolution of Solar Magnetograms via Adaptive Stratified Ensemble Learning with Uncertainty Estimation

Support-Compiled Feature Folding: More Evidence at Lower Memory Across Tabular Foundation Models

TEEP-RCNN: Texture-Enhanced Edge-aware Perception for Steel Surface Defect Detection via Improved Convolutional Block Attention in Faster R-CNN

TEMPS: Temporal Sentence Embeddings for Temporal Information Retrieval

The three things today's hottest startups are looking for in their AI stack

TwinCheck: Evidence-Grounded Negative-Twin Verification for Stateful Tool Agents

VLMs Can Describe, But Not Measure: Object-Centric Scene Understanding for Robotic Manipulation

What Do Tabular Foundation Models Compute In Context? In-Situ Representation Refinement through Attention-Gated Updates

WhatWorkedBench: Benchmarking Experimental Understanding in AI Agents

When Adaptation Hurts: Split Sensitivity and Person-Level Negative Transfer in Federated Wearable Onboarding

When Labels Are Scarce: An Oscillatory State Space Model for Vibration Diagnosis

Where Should I Join? Robot Group Joining via Language-Guided Goal Prediction

WTF?! Simulation-Free Reinforcement Learning with Wasserstein-Tilted Flow Maps

A guide to speeding up your video processing with AlphaEvolve

AgentBetta: Verification-Driven Adaptive Configuration of an AI Nano-Agent through Selective Expansion and Verified Contraction

AIBuildAI-2.5: Efficient Autonomous AI Model Development Through LLM-Guided Tree Search

b11132

BAS-OPD: Budget-Aware Selective On-Policy Self-Distillation for Fine-Grained Multimodal Perception

Bayesian Fusion of Active Contour Models and ConvNet Priors for Standing Dead Tree Segmentation

ChemVTS-Bench: Evaluating Visual-Textual-Symbolic Reasoning of Multimodal Large Language Models in Chemistry

Construting Reverse Thinking: Developing Large Language Models' Reverse Thingking Ability

CricRAG: Retrieval Augmented Vision-Language Models for Personalized Cricket Coaching

Decoding Order Matters in Autoregressive Speech Synthesis

DeepFEAv2: Deep Learning for Transient Finite Element Analysis Beyond Structured Meshes

Delving into Asymmetric Information Dynamics for High-Fidelity Virtual Try-On

Diffusion Drafts, AR Verifies: Accelerating Document OCR with Self-Speculative Decoding

Directional Total Variation-Regularized Implicit Neural Representations (DTV-INR) for Continuous Super-Resolution in Degraded Imaging Domains

Do Implicit Personalization and Explicit Styles Conflict? PsPLUG: A Lightweight Plug-in for Balancing Personalization and Style in Customized LLMs

DP-Splat: Bayesian Nonparametric Complexity Control for Gaussian Splatting