Skip to content
View Glupayy's full-sized avatar

Highlights

  • Pro

Block or report Glupayy

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

Related code, checkpoints and project page for V-Reflection

Python 48 Updated Apr 7, 2026

Official implementation of Seeing with You: Perception-Reasoning Co-evolution for Multimodal Reasoning.

Python 35 1 Updated Apr 6, 2026

A Guided Reinforcement Learning framework enhancing MLLM reasoning via process-level verification and collaborative rollout strategies.

Python 47 1 Updated Mar 3, 2026

[CVPR 2026 Highlight] Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding

Python 81 5 Updated Apr 9, 2026

Official Implementation (Pytorch) of the "Representation Shift: Unifying Token Compression with FlashAttention", ICCV 2025

Python 34 2 Updated Feb 22, 2026

[ICLR'26] Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology

Python 81 2 Updated Jan 26, 2026

An implementation of the hallucination mitigation method "REVIS" introduced in "Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models"..

Python 8 Updated Feb 12, 2026

v1: Learning to Point Visual Tokens for Multimodal Grounded Reasoning

Python 19 1 Updated Oct 6, 2025
Jupyter Notebook 73 13 Updated Oct 9, 2025

Do LLMs and VLMs Share Neurons for Inference? Evidence and Mechanisms of Cross-Modal Transfer

Python 2 Updated Feb 22, 2026

Shaping capabilities with token-level pretraining data filtering

Python 94 6 Updated Jan 28, 2026

FROM $f(x)$ AND $g(x)$ TO $f(g(x))$: LLMs Learn New Skills in RL by Composing Old Ones

Python 65 6 Updated Jan 26, 2026

Codes and Data for ICLR 2026 paper "LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical Supervision"

Python 18 1 Updated Feb 25, 2026

[ICLR 2026] "VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool Use"

Python 172 6 Updated Mar 20, 2026

✨✨ [ICLR 2026] Think Beyond Images

Python 580 37 Updated Sep 23, 2025

Pixel-Level Reasoning Model trained with RL [NeuIPS25]

Python 292 11 Updated Nov 6, 2025

CoCoT generate datasets

Python 8 Updated Jan 18, 2026

The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]

Python 188 7 Updated Jun 5, 2025

[CVPR 2025 (Oral)] Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key

Python 108 4 Updated Jan 9, 2026
Python 123 13 Updated Jul 22, 2025

The official repo for "Where do Large Vision-Language Models Look at when Answering Questions?"

Python 63 8 Updated Jan 7, 2026

Code for Reducing Hallucinations in Vision-Language Models via Latent Space Steering

Python 110 7 Updated Nov 23, 2024

Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".

Python 376 98 Updated Jun 13, 2025
Python 10 3 Updated Sep 13, 2024

[ACML 2025] Conformal Abstention for LLMs and VLMs

Python 6 2 Updated Feb 13, 2025

Conformal prediction for controlling monotonic risk functions. Simple accompanying PyTorch code for conformal risk control in computer vision and natural language processing.

Python 80 11 Updated Jan 23, 2023

A scikit-learn-compatible library for estimating prediction intervals and controlling risks, based on conformal predictions.

Jupyter Notebook 1,535 136 Updated Apr 17, 2026

Resources and paper list for "Thinking with Images for LVLMs". This repository accompanies our survey on how LVLMs can leverage visual information for complex reasoning, planning, and generation.

1,422 42 Updated Mar 9, 2026

[ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation

Python 141 12 Updated Sep 11, 2025
Next