List your company

Research

Tasks

Explore the problems researchers are working on and the benchmarks used to measure progress.

4,899 tasksPage 102 of 196

Reset

Tasks

TaskDomainBenchmarksPapersLast update
End-to-end Attention Latencyllm chat instruction11Apr 2, 2026
Model Merging Performance Aggregationmultimodalllm chat instruction+211Feb 18, 2026
Agentic Instruction Followingagents tool usellm chat instruction11Feb 19, 2026
Plausibilityretrieval search ragllm chat instruction11Apr 2, 2026
Model Utility Maintenancellm chat instruction11Feb 19, 2026
Intent-conditioned model selectionllm chat instruction11Apr 2, 2026
Interaction Alignment (User Study)llm chat instruction11Feb 18, 2026
Multi-task Agent Executionagents tool usellm chat instruction11Apr 2, 2026
Jailbreak and Phishing Prompt Classificationadversarial safety securityllm chat instruction11Apr 2, 2026
Jailbreak Prompt Classificationadversarial safety securityllm chat instruction11Apr 2, 2026
Individual Alignment (User Study)llm chat instruction11Feb 18, 2026
Expert Red Teamingadversarial safety securityllm chat instruction11Feb 19, 2026
General-purpose Multimodal Understandingmultimodalllm chat instruction12May 26, 2026
Offline Synthetic Data Generationllm chat instruction11Apr 2, 2026
Turn-level dialogue quality evaluation (Uses Knowledge)llm chat instructionnlp11Feb 18, 2026
LLM Evaluation Agreementllm chat instruction11Feb 18, 2026
Phrase Protectionadversarial safety securityllm chat instruction11Feb 19, 2026
Housing Consultationllm chat instruction11Apr 2, 2026
Spatial Navigation and Reasoningrobotics embodied aillm chat instruction11Apr 2, 2026
Proactive Agent Task Executionagents tool usellm chat instruction11Apr 2, 2026
Multi-session Psychological Counselingllm chat instruction11Apr 2, 2026
Hallucination Evaluation (Discriminative)llm chat instructionnlp11Apr 2, 2026
Hallucination Evaluation (Generative)llm chat instruction12May 7, 2026
Moral Drift Characterizationllm chat instructionadversarial safety security11Apr 2, 2026
LLM Judge Agreementllm chat instructionadversarial safety security11Feb 18, 2026