Marshall Guo

weathon

36 21 7

weathon

AI & ML interests

None yet

Recent Activity

published a model about 9 hours ago

weathon/bisexual_grpo_exp

published a model about 17 hours ago

weathon/bisexual_grpo_abl3

published a model about 19 hours ago

weathon/bisexual_grpo_abl2

View all activity

Organizations

None yet

upvoted a paper 9 days ago

Order-Only On-Policy Distillation

Paper • 2611.02112 • Published 12 days ago • 36

upvoted 2 papers 3 months ago

Coding-agents can replicate scientific machine learning papers

Paper • 2607.02134 • Published Jul 10 • 2

Stealing Reasoning Traces from Proprietary LLM APIs

Paper • 2608.09867 • Published Aug 10 • 119

upvoted a paper 5 months ago

JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting

Paper • 2606.18394 • Published Jun 25 • 36

upvoted 2 papers 9 months ago

On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification

Paper • 2508.05629 • Published Aug 7, 2025 • 183

FaceLinkGen: Rethinking Identity Leakage in Privacy-Preserving Face Recognition with Identity Extraction

Paper • 2602.02914 • Published Feb 2 • 3

upvoted 2 papers 10 months ago

Presenting a Paper is an Art: Self-Improvement Aesthetic Agents for Academic Presentations

Paper • 2510.05571 • Published Oct 7, 2025 • 15

Exploring Vision Language Models for Facial Attribute Recognition: Emotion, Race, Gender, and Age

Paper • 2410.24148 • Published Oct 31, 2024 • 3

upvoted an article 10 months ago

Article

(LoRA) Fine-Tuning FLUX.1-dev on Consumer Hardware

derekl35, marcsun13, sayakpaul, merve, linoyts

•

Jun 19, 2025

• 108

upvoted a paper 11 months ago

Aesthetic Alignment Risks Assimilation: How Image Generation and Reward Models Reinforce Beauty Bias and Ideological "Censorship"

Paper • 2512.11883 • Published Dec 9, 2025 • 6

upvoted an article 11 months ago

Article

Unified Models for Image Understanding and Generation: Understanding Cutting-Edge Model Architectures

exploding-gradients

•

Sep 15, 2025

• 5

upvoted 2 papers 12 months ago

TIIF-Bench: How Does Your T2I Model Follow Your Instructions?

Paper • 2506.02161 • Published Jun 2, 2025 • 13

TiDAR: Think in Diffusion, Talk in Autoregression

Paper • 2511.08923 • Published Nov 12, 2025 • 129

upvoted 4 papers about 1 year ago

Diffusion Language Models are Super Data Learners

Paper • 2511.03276 • Published Nov 5, 2025 • 132

VSF: Simple, Efficient, and Effective Negative Guidance in Few-Step Image Generation Models By Value Sign Flip

Paper • 2508.10931 • Published Aug 11, 2025 • 1

Position: The Pitfalls of Over-Alignment: Overly Caution Health-Related Responses From LLMs are Unethical and Dangerous

Paper • 2509.08833 • Published Aug 27, 2025 • 1

CamSAM2: Segment Anything Accurately in Camouflaged Videos

Paper • 2503.19730 • Published Mar 25, 2025 • 1

upvoted 3 papers over 1 year ago

NegVSR: Augmenting Negatives for Generalized Noise Modeling in Real-World Video Super-Resolution

Paper • 2305.14669 • Published May 24, 2023 • 2

ZS-VCOS: Zero-Shot Video Camouflaged Object Segmentation By Optical Flow and Open Vocabulary Object Detection

Paper • 2505.01431 • Published Apr 10, 2025 • 1

LDM3D: Latent Diffusion Model for 3D

Paper • 2305.10853 • Published May 18, 2023 • 13