127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “models”

95,172 results

Model Releases

b11597

DGX agent

graph: skip the LM head for pooled embeddings (#30445) graph: skip the LM head for pooled embeddings A context that extracts pooled embeddings outputs one vector per sequence, but every model still ex

model-releasesllama-cpp-releases

13 Oct 2026

Model Releases

Horsey challenge | Strata Fork | Qwen 3.8 FN NVFP4

DGX agent

So I wanted to try the horsey challenge myself on the latest engine i been testing which is a strata fork by sergqwer. https://github.com/sergqwer/strata-nvfp4. I seen a post earlier and seen i believ

Search: “models”

b11597

Horsey challenge | Strata Fork | Qwen 3.8 FN NVFP4

SonicBoom: 52 tok/s decode on a laptop RTX 3050 (llama.cpp: 45) with the same quantized kernels, the difference is a graph compiler. No Python.

AdaC-GRPO: Towards Mastering Long-Horizon Visual Sudoku Puzzles via Adaptive Curriculum Learning

AMLworld-Compact: Importance-Weighted Downsampling for Cost-Effective LLM Evaluation and Error Diagnosis

BrokenML: can agents fix broken ML jobs?

BT-Agent: Deploying Onboard Robot Agents with Behavior Trees and Multi-Fidelity Evaluation

CORE-Seg: Reasoning-Driven Segmentation for Complex Lesions via Reinforcement Learning

Golden Anchor for Video Generation

Improve my vibe-slopped pipeline

Kernelized Parameter Sensitivity Atlases for Amortized Conditional Interpretability

ManeuverFlow: Maneuver Hypothesis Generation with Future Evidence for Trajectory Evaluation and Refinement in End-to-End Autonomous Driving

MVGraph: Benchmarking LVLMs on Evidence Composition across Multi-View Visual Graph

PlacePulse: Learning Transferable Place Representations from Structural Geographic Data

QTestBench: A Test Framework for Evaluating LLM-Generated Quantum Code

Reflective Prompt Optimization of a Deep-Research Agent: A Topic-Disjoint, Multi-Seed Protocol for Measuring Transferable Gains and Prompt-Level Overfitting

Same Query, Different Answer: Run-to-Run Variance in Semantic Query Processing

The Alignment Veto: How Safety Training Suppresses Cultural Knowledge in LLMs

When Edge Independence Fails: Joint Graph Diffusion with Latent Sociability Priors

A new work suggesting that division of labor among self-improving AI agents can help them avoid reinforcing their own errors. I found this w…

'Strata' for GLM5.3 Flash is here for some! Project Maya

vllm-ascend updates (GLM5.3-flash) on dual 310p Ascend cards

48Gb VRAM speed AND quality ! (Qwen 3.8 27B Swift 1.5 W8A16)

Mreaia v1.0.0: Universal Zero-Token Engine & Hardware-Locked Context Distillation for LLMs (>99.9% Reduction)

Agentic-TTT: Training test-time policy for test-time training

Amortized Off-Policy Evaluation for LLMs

Boosting the Local Invariance for Better Adversarial Transferability

CAFE: Causal Black-Box Testing of Machine Unlearning

Cited but Not Consulted: A Counterfactual Audit of Legal Chain-of-Thought Faithfulness

Class Machine Unlearning for Complex Data via Concepts Inference and Data Poisoning

Closed-loop evaluation of LLM agents for embedded software development

Dynamic Free-Rider Detection in Cross-Silo Federated Learning via Simulated Attack Patterns

Examining Social Attribution in LLM Reasoning: A Theory-Guided Probing Methodology

FastBench: Can Streaming VLMs Perceive High-Dynamic Real-World Streams?

How Narrative Wrapping Affects LLM Refusal: A Cross-Language Benchmark and Defense

Invariant-Measure Reasoners: Stable Representations for Latent Reasoning

My 'Anthropic/ChatGPT in a box' is... now open source and publicly hosted on Github.

Narrow and Deep: An Ontology Tower as the Knowledge of an LLM Agent for an Industrial Equipment System

Nullify: Null-Space Activation Steering for Training-Free LLM Unlearning

Obscuring Data Contamination Through Translation: Evidence from Arabic Corpora

ProtoSemImage: Image-Valued Prototypes with Deformable Row Alignment for Interpretable Document Classification

RAG-Stress: Probing the Limits of Evidence Reliance in Retrieval-Augmented Generation

SignRAG: Unified Retrieval-Augmented Gloss-Free Sign Language Translation

TestJack: Should you trust the results in coding benchmarks? Agentic Coding Benchmarks Auditing via Evaluator Evolution

ThinkingBox: Solving an agent task once vs. solving it 20/20: 507 stateful workflows graded on terminal database state [R]

Training on the Future: A Delay-Aware Audit of Test-Time Adaptation for Time-Series Forecasting

Where to Adapt Matters: Layer-Selective Fine-Tuning for Capability Retention

Adjoint-Based Calibration and Optimal Control of Stochastic Multiscale Bioprocess Digital Twins