Peng Shangpin

psp-dada's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 4 papers 4 days ago

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents

Paper • 2605.07630 • Published 30 days ago • 1

Chronicles-OCR: A Cross-Temporal Perception Benchmark for the Evolutionary Trajectory of Chinese Characters

Paper • 2605.11960 • Published 26 days ago • 1

PhoneWorld: Scaling Phone-Use Agent Environments

Paper • 2605.29486 • Published 10 days ago • 10

ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats

Paper • 2606.01348 • Published 7 days ago • 2

upvoted a paper 22 days ago

Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe

Paper • 2605.03677 • Published May 5 • 27

upvoted an article 5 months ago

view article

Article

LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family

• 

lightonai

•

Jan 19

• 94

upvoted a paper 6 months ago

HunyuanOCR Technical Report

Paper • 2511.19575 • Published Nov 24, 2025 • 23

upvoted 2 collections 8 months ago

Hallucinations

Collection

17 items • Updated Sep 8, 2025 • 1

Hallucination

Collection

1 item • Updated Oct 10, 2025 • 1

upvoted a paper 10 months ago

HLFormer: Enhancing Partially Relevant Video Retrieval with Hyperbolic Learning

Paper • 2507.17402 • Published Jul 23, 2025 • 5

upvoted a collection 10 months ago

SENTINEL

Collection

[ICCV 2025] Official repository of "Mitigating Object Hallucinations via Sentence-Level Early Intervention". Repo: https://github.com/pspdada/SENTINEL • 9 items • Updated Feb 16 • 4

upvoted 2 papers 11 months ago

Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMs

Paper • 2506.10054 • Published Feb 11 • 3

Mitigating Object Hallucinations via Sentence-Level Early Intervention

Paper • 2507.12455 • Published Jul 16, 2025 • 9

upvoted a paper about 1 year ago

A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce

Paper • 2504.11343 • Published Apr 15, 2025 • 20

upvoted a paper over 1 year ago

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Paper • 2406.18629 • Published Jun 26, 2024 • 42

upvoted an article almost 2 years ago

view article

Article

Llama 3.1 - 405B, 70B & 8B with multilinguality and long context

• 
• 
• +6

philschmid, osanseviero, alvarobartt, lvwerra, dvilasuero, reach-vb, marcsun13, pcuenq

•

Jul 23, 2024

• 241