127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

All entries

127,604 results

Model Releases

b10889

DGX agent

memory : avoid allocating V cache for indexer (it's not used) (#28330) Co-authored-by: Stanisław Szymczyk sszymczy@gmail.com Website: https://llama.app Attestations: https://github.com/ggml-org/llama.

model-releasesllama-cpp-releases

10 Sept 2026

Model Releases

b10891

DGX agent

vulkan: fall back to shared-memory reduction for dmmv on PowerVR (#28341) The Imagination proprietary Vulkan compiler returns VK_ERROR_UNKNOWN from vkCreateComputePipelines for every dequant mul_mat_v

model-releases

All entries

b10889

b10891

b10892

b10893

b10894

b10896

b10897

b10899

b10900

b10901

Bag of Tricks or Bag of Myths? Reducing Modeling Complexity with Task Knowledge in Explainable Suicide Risk Assessment

Bait-and-Recover: Poisoning Internal Refusal Signals to Defend LLMs against White-Box Editing Jailbreaks

Bayesian Adversarial Privacy

Bayesian deep learning integration of geophysical and drilling data for 3D prediction of copper mineralization and drill targeting: a case study from the Kogodai prospect, Rudny Altai

Behavioral Grammar: Detecting Adaptive Malware via Tiny Language Model Priors and Second-Order Temporal Analysis

Belief-State Engine: Augmenting LLMs for Principled Planning Under Partial Observability

Benchmark Scores Are Pipeline-Dependent: A Reliability Audit of Cybersecurity LLM Benchmarks

Benchmarking Hybrid Deep Research Across Database Querying and Web Search

BETA-Labeling for Multilingual Dataset Construction in Low-Resource IR

Better Together: Complementary Query Rewriting Under a Strong RAG Baseline

Beyond 'AI Helps Humans': Decision-Targeted Evaluation Design for Human-Agent Teams in the Agentic Era

Beyond Coherence: Benchmarking Professional Editing-Technique Execution in Multi-Shot Audio-Video Generation

Beyond Contact Sensors: Deep learning with Pseudo-Labeling for remote Photoplethysmography

Beyond Conventional Federated Learning via High-Order Regularization

Beyond Cross-Lingual Transfer: Benchmarking Propagation Boundaries in Multilingual LLM Unlearning

Beyond Final Decisions: A Process-Centric Benchmark for Transparent AI-Assisted Peer Review

Beyond One-Shot Expansion: Contrastive Evidence Exploration for Multi-Hop Retrieval

Beyond One-Size-Fits-All: Neural Networks for Differentially Private Tabular Data Synthesis

Beyond One-Size-Fits-All: Sample-Adaptive Strategy Routing for Vision Token Pruning in MLLMs

Beyond Prompts: Measuring and Optimizing LLM Tool-Agent Harnesses

Beyond Retrieval: Joint Supervision and Multimodal Document Ranking for Textbook Question Answering

Beyond Right and Wrong: Evaluating Second-order Social Reasoning in Large Language Models

Beyond Similarity: Foundation Models as an Efficient Backbone for Training-Free Composed Video Retrieval

Beyond Single-Negative Preference: Multi-Negative DPO for LLM-Centric Historical Entity Linking

Beyond Sparse Rewards: A New Benchmark and Structure-Aware Graph Alignment for Micro-Drama Understanding

Beyond Top-k Skill Retrieval: Diversity-Aware Skill Routing for LLM Agents

Beyond Top Words: MonoTM for Topic Modeling with Interpretable Monosemantic Features

Beyond Weak Labels: Prompt-Guided Local Refinement for Weakly Supervised Water Segmentation in High-Resolution Multispectral Imagery

Big overhaul on DeepSeek V4.1 using an encoder-decoder setup. Tbh they should have called it DeepSeek V5! Super cool and refreshing, though!

Bilevel Planning with Learned Symbolic Abstractions from Interaction Data

BIO-MEMART: Biometric-Aware KV Cache Memory for Multi-User LLM Agents

Boots on the Ground: ‘WARDOGS’ Goes All Out on GeForce NOW at Early-Access Launch

BRACE: Anchored Bellman-Residual Correction for Stale Critics in Asynchronous RL

BrainTaskonomy: Learning How to Pretrain and What to Transfer in fMRI Foundation Models

Bridging the Semantic-Utility Gap in Multimodal RAG via Generator-in-the-Loop Alignment

Bridging Theory and Data: Correcting Nuclear Mass Models with Interpretable Machine Learning

BTBR: A Bayesian-Theory-Driven Probabilistic-Fuzzy Framework for Implicit Bias Removal in Large Language Models

Build an end-to-end RFI questionnaire workflow using Amazon Quick Automate