logo

logo

ResearchPapers

Explore 2077AI's published papers on AI innovation, ethical frameworks, and generative models. Designed for researchers and developers, it bridges theory with real-world impact. Download, cite, and collaborate to advance AI's future.

Title
Aspect
Date
SIN-Bench: Tracing Native Evidence Chains in Long-Context Multimodal Scientific Interleaved Literature
Multimodal, Benchmark
26-01
NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents
Agent, Benchmark
25-12
COIG-Writer: A High-Quality Dataset for Chinese Creative Writing with Thought Processes
Multimodal, Dataset
25-10
A^2FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning
Agent, Model
25-10
ACADREASON: Exploring the Limits of Reasoning Models with Academic Research Problems
Reasoning, Benchmark
25-10
OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs
Multimodal, Benchmark
25-10
Towards Personalized Deep Research: Benchmarks and Evaluations
Agent, Benchmark
25-09
VideoScore2: Think before You Score in Generative Video Evaluation
Multimodal, Benchmark
25-09
IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?
Multimodal, Benchmark
25-09
EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing
Multimodal, Model
25-09