127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “models”

95,135 results

Model Releases

Shieldstral

DGX agent

arXiv:2607.25857v1 Announce Type: new Abstract: We introduce Shieldstral, a 3B-parameter policy-adaptive multimodal safety classifier that matches or outperforms models nearly 7imes its size on text s

model-releasesarxiv-cs-cl

29 Jul 2026

Model Releases

TabRank: Chain-of-Thought Distillation for Table Re-Rankers

DGX agent

arXiv:2607.25182v1 Announce Type: cross Abstract: The ability to retrieve relevant tables for answering questions is a key task for structured information retrieval. Multi-stage retrieval systems rely

Search: “models”

Shieldstral

TabRank: Chain-of-Thought Distillation for Table Re-Rankers

TimeCapsule: Generative Hallucination as a Method for Historical Sensemaking

Toward an Organizational Science of Multi-Agent LLM Systems: Decoupling Who, How, and Which Algorithm

A Mechanistic Perspective and Circuit-Guided Difficulty Metric for Unlearning

Adaptive Multi-Scale Forecasting and Gate-Localized Conformal Prediction for Multivariate Nonstationary Time Series

Adversarial Test-Hardening for AI-Written Code: An Instrument Autopsy and a Pre-Registered Causal Estimate of the Critic Loop

AlloBench: Measuring Online Tool Allocation Capability in LLM Agents

AptAvatar: Fast and Vivid Long-Form Audio-Driven Video Generation for Production-Ready Avatars

AssumptionMiner: Extracting, Tracing, and Revising Implicit Assumptions in LLM Code Generation

Between Suppression and Collapse: Evaluating Narrative Unlearning with LENS

Compressing LLMs with MoP: Mixture of Pruners

Context-Aware Concept Distillation for Trustworthy Flood Prediction

Cost-Aware Recovery-Pathway Identification and Bayesian Optimization for Autonomous Materials Discovery

Covariance-Boosted Gaussian Processes for Spatiotemporal Irregularities

Data Pyramid for Embodied Manipulation

Do LLMs Know Their Vulnerable Scenarios?

DocHRL: A Hierarchical Reinforcement Learning Framework for Cost-Optimised Document Classification

DriveDNA: A Large-Scale Multimodal Naturalistic Driving Dataset and Benchmark for Driving Style Identification

FilmBench: A Film-Grade Benchmark for Cinematic Video Generation

I built a tool to actually test which weights matter before quantizing, instead of guessing (Qwen3.6-27B, 3 builds: Bedrock/Tightrope/Gambit)

If I only went off X posts, I'd think Ramp was an AI lab

LA-RL: Label-Aware Self-Reflection for Reinforcement Learning in Information Extraction

Language Shapes Instruction Hierarchy Compliance in Multilingual LLMs

Mixture-of-Thought-Tokens: Unifying Perception and Reasoning for Free-form Multimodal Grounding

Multi-Modal Scene Graph with Kolmogorov-Arnold Experts for Audio-Visual Question Answering

Neuromorphic Object Detection: An In-Depth Study and Future Directions

No Optimal Language Set Exists for Multilingual Instruction Tuning: Insights from a Linguistically-Informed Study

On the Impossibility of Unbiased and Length-Invariant Policy Optimization with Outcome Rewards

OpenAIs HealthBench in Action: Evaluating an LLM-Based Medical Assistant on Realistic Clinical Queries

Parameter-Efficient Adaptation of SAM3 for Prompt-Driven Surgical Concept Segmentation

ParBench: A Benchmark for Reliable Evaluation of LLM Parallel Code Translation

Phenology-based learning framework for yield estimation and harvest forecasting of raspberry fruits

Poison to Detect: Detection of Targeted Overfitting in Federated Learning

Poster: Rethinking Security in LLM Code Generation through Real-World Risk Scenarios

Random Forest-Based Prediction of Bone Volume Fraction and Fracture Position from S-Parameters

Same Question, Different Answers: Evaluating LLM Reliability Beyond Accuracy

Semalith v1.4: A Calibrated 184M Safety Classifier Achieving State-of-the-Art Prompt-Injection Detection at 44x Fewer Parameters than Llama-Guard-3-8B

Source-Free Controlled Adaptation of Teachers for Continual Test-Time Adaptation

Spatial-IQ: Deconstructing Spatial Intelligence via Hierarchical Capability Tests

TextRich: A Multi-Domain Benchmark for Detecting AI-Generated Text-Rich Images from GPT-Image-2

TokenMem: Faithful Knowledge Injection for Frozen LLMs

VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference

Weighted Low-Rank Matrix Approximation: Acceleration and Applications

XGRVFL-MV: Residual-Coupled Graph-Embedded Multi-View Random Vector Functional Link Network with FleXi Guardian Loss

Data Quality over Capacity: Internalizing Documents into LoRA Adapters for Closed-Book QA

Do emulated quantum circuits change what CNNs look at? Performance and explainability comparison in medical image classification

Filling Before Advancing: Capability-Gap-Driven Post-Training for Scenario-Specialized Remote Sensing MLLMs