Zhangyang “Atlas” Wang

papers

543

total citations

papers (12)

FSGS: Real-Time Few-shot View Synthesis using Gaussian Splatting

ECCV 2024arXiv

297

citations

DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting

ECCV 2024arXiv

citations

Efficient-3Dim: Learning a Generalizable Single-image Novel-view Synthesizer in One Day

ICLR 2024arXiv

citations

SPIN-Bench: How Well Do LLMs Plan Strategically and Reason Socially?

COLM 2025arXiv

citations

Can Test-Time Scaling Improve World Foundation Model?

COLM 2025arXiv

citations

More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment

COLM 2025arXiv

citations

LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning

COLM 2025arXiv

citations

LLaMaFlex: Many-in-one LLMs via Generalized Pruning and Weight Sharing

ICLR 2025

citations

Zhangyang “Atlas” Wang

papers (12)

FSGS: Real-Time Few-shot View Synthesis using Gaussian Splatting

DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting

DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer

SEAL: Steerable Reasoning Calibration of Large Language Models for Free

Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality

SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training

Efficient-3Dim: Learning a Generalizable Single-image Novel-view Synthesizer in One Day

SPIN-Bench: How Well Do LLMs Plan Strategically and Reason Socially?

Can Test-Time Scaling Improve World Foundation Model?

More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment

LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning

LLaMaFlex: Many-in-one LLMs via Generalized Pruning and Weight Sharing

papers (12)

FSGS: Real-Time Few-shot View Synthesis using Gaussian Splatting

DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting

DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer

SEAL: Steerable Reasoning Calibration of Large Language Models for Free

Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality

SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training

Efficient-3Dim: Learning a Generalizable Single-image Novel-view Synthesizer in One Day

SPIN-Bench: How Well Do LLMs Plan Strategically and Reason Socially?

Can Test-Time Scaling Improve World Foundation Model?

More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment

LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning

LLaMaFlex: Many-in-one LLMs via Generalized Pruning and Weight Sharing