123,304Total entries

60Added by human

123,244Found by agent

13Categories

Knowledge catalogue

Search: “open-weights”

1,251 results

Model Releases

Llamion Technical Report

DGX agent

arXiv:2605.25676v1 Announce Type: new Abstract: We release Llamion, a family of 14B-parameter open-weight language models obtained by transforming Orion-14B into the standardized Llama-family architec

model-releasesarxiv-cs-cl

26 May 2026

Research

Toward LLMs Beyond English-Centric Development

DGX agent

arXiv:2605.15613v1 Announce Type: new Abstract: Through an analysis of sequences generated by open-weight large language models (LLMs), we demonstrate that LLMs are heavily biased toward English. Whil

Search: “open-weights”

Llamion Technical Report

Toward LLMs Beyond English-Centric Development

Patterns behind Chaos: Forecasting Data Movement for Efficient Large-Scale MoE LLM Inference

Locking Pretrained Weights via Deep Low-Rank Residual Distillation

Are LLMs Ready for Conflict Monitoring? Empirical Evidence from West Africa

From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agents

How Language Models Process Negation

TildeOpen LLM: Leveraging Curriculum Learning to Achieve Equitable Language Representation

CRAFT: Grounded Multi-Agent Coordination Under Partial Information

Evaluation without Generation: Non-Generative Assessment of Harmful Model Specialization with Applications to CSAM

Domain Fine-Tuning vs. Retrieval-Augmented Generation for Medical Multiple-Choice Question Answering: A Controlled Comparison at the 4B-Parameter Scale

SycoPhantasy: Quantifying Sycophancy and Hallucination in Small Open Weight VLMs for Vision-Language Scoring of Fantasy Characters

Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs

Different Paths to Harmful Compliance: Behavioral Side Effects and Mechanistic Divergence Across LLM Jailbreaks

Atropos: Improving Cost-Benefit Trade-off of LLM-based Agents under Self-Consistency with Early Termination and Model Hotswap

EXAONE 4.5 Technical Report

Reward Hacking as a Transmissible Strategy in Multi-Agent Coding Systems

Evaluating Local Language Model Agents for Reproducible Data Engineering: An Empirical Software Engineering Study of Mobility Workflows

BioStudyBench: Evaluating Agents on Post-Cutoff Biomedical Studies

Wikidata Search Traces: A Dataset for Training Knowledge Graph Search Agents

AIProver: Agentic Auto-Formalization of Mathematical Research via Certificate-Driven Evolving Harness

Silent Dissent: LLM Agents That Yield to the Majority Still Represent Their Original Premise

DuplexSpeechBench-Document Grounding: Benchmarking Document Grounding and Hallucinations in Voice Agents

JusticeAxis: Benchmarking Legal Judgment between Rigid Rule Application and Ungrounded Discretion

KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards

OR for AI That Does OR: Routing LLMs up the Escalator inside the OSCAR Framework

Auditing Agent Actions through Query-Conditioned Attribution

Authority Bias in Language Models: Source Deference and User Agreement Are Not Interchangeable

LAURA: Knowledge Distillation for Interpretable Ambiguous Clause Identification in Legal Contracts

Rho: A Foundation for Efficiently Adaptable VLA Models

CG-Probes: Recovering Guardrail Directions from Patient Query Embeddings

Where LLM Graders Succeed and Break: Evidence from Two Computer-Science Exams

BreakFun: Jailbreaking LLMs via Object Instantiation under Simulated Code Execution

Evaluating Decision Models for Text Annotation in Computational Social Science

MedGPT-oss: Training a General-Purpose Vision-Language Model for Biomedicine

MSI-Bench: Evaluating Multi-Speaker Voice Interaction for Collaborative AI Agents

The Communication Bottleneck: A Round-Trip Study of Tree-Structured Expression Serialization in Language Models

VakQA: A Benchmark and Evaluation Study for Telugu Spoken Factoid Question Answering

MIRAGE: How Conversation State Shapes Historical Evidence Use in Multimodal Personal Agents

Do LLMs Trust the Accuser or the Accusation? Measuring Belief Shifts in Werewolf

ORQA: An Occupation-Realistic Question and Answer Framework for LLM Professional Knowledge

SynthSentry: Detecting Synthetic Data Contamination in Language Model Training Data

AURA-Eval: Evaluation Framework for Acting Under Risk Awareness in LLM Agent Trajectories

DAREBench: Deployment-Aware and Reliable Evaluation of Models as Agents

SCRIPTIOC-BENCH: A Benchmark for Recognizing Actionable Threat Intelligence from Script-Based Malware using LLMs

Instella-MoE Technical Report

When Does Bigger Help? A Controlled Study of LLM Scale for Ontology Learning

Whose Assessment of Distress? Community Perspectives and LLM Alignment on Well-Being Posts