Tianyu Liu

papers

410

total citations

papers (10)

Omni-MATH: A Universal Olympiad Level Mathematic Benchmark for Large Language Models

ICLR 2025arXiv

149

citations

VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models

CVPR 2025arXiv

citations

Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving

NEURIPS 2025arXiv

citations

TorchTitan: One-stop PyTorch native solution for production ready LLM pretraining

ICLR 2025

citations

MuSe-GNN: Learning Unified Gene Representation From Multimodal Biological Graph Data

NEURIPS 2023arXiv

citations

Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing

CVPR 2022arXiv

citations

Learning Rule-Induced Subgraph Representations for Inductive Relation Prediction

NEURIPS 2023arXiv

citations

Tianyu Liu

papers (10)

Omni-MATH: A Universal Olympiad Level Mathematic Benchmark for Large Language Models

VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models

Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving

TorchTitan: One-stop PyTorch native solution for production ready LLM pretraining

MuSe-GNN: Learning Unified Gene Representation From Multimodal Biological Graph Data

Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing

Learning Rule-Induced Subgraph Representations for Inductive Relation Prediction

Language Models over Canonical Byte-Pair Encodings

Rectify the Regression Bias in Long-Tailed Object Detection

INT2: Interactive Trajectory Prediction at Intersections

papers (10)

Omni-MATH: A Universal Olympiad Level Mathematic Benchmark for Large Language Models

VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models

Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving

TorchTitan: One-stop PyTorch native solution for production ready LLM pretraining

MuSe-GNN: Learning Unified Gene Representation From Multimodal Biological Graph Data

Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing

Learning Rule-Induced Subgraph Representations for Inductive Relation Prediction

Language Models over Canonical Byte-Pair Encodings

Rectify the Regression Bias in Long-Tailed Object Detection

INT2: Interactive Trajectory Prediction at Intersections