Cover Image

CircuitProbe: Tracing Visual Temporal Evidence Flow in Video Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Yiming, Zhao, Zhuokai, Yu, Chengzhang, Wang, Kun, Chu, Zhendong, Li, Qiankun, Chen, Zihan, Liu, Yang, Ding, Zenghui, Sun, Yining, Wen, Qingsong
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding
by: Zhang, Yiming, et al.
Published: (2024)

RankCLIP: Ranking-Consistent Language-Image Pretraining
by: Zhang, Yiming, et al.
Published: (2024)

CircuitProbe: Predicting Reasoning Circuits in Transformers via Stability Zone Detection
by: Panuganti, Rajkiran
Published: (2026)

FRAME: Feedback-Refined Agent Methodology for Enhancing Medical Research Insights
by: Yu, Chengzhang, et al.
Published: (2025)

The Paradox of Outcome Optimization: A Causal Information-Theoretic Bound on Reasoning Shortcuts in LLMs
by: Chen, Zihan, et al.
Published: (2026)

Rethinking RL Evaluation: Can Benchmarks Truly Reveal Failures of RL Methods?
by: Chen, Zihan, et al.
Published: (2025)

UniEDU: A Unified Language and Vision Assistant for Education Applications
by: Chu, Zhendong, et al.
Published: (2025)

IIMedGPT: Promoting Large Language Model Capabilities of Medical Tasks by Efficient Human Preference Alignment
by: Zhang, Yiming, et al.
Published: (2025)

Multimodal AI Teacher: Integrating Edge Computing and Reasoning Models for Enhanced Student Error Analysis
by: Tianlong Xu, et al.
Published: (2025)

Scalar curvature rigidity of parabolically convex domains in hyperbolic spaces
by: Sun, Chengzhang
Published: (2024)

$L^2$-torsion of fibrations
by: Sun, Chengzhang
Published: (2024)

AI-Driven Virtual Teacher for Enhanced Educational Efficiency: Leveraging Large Pretrain Models for Autonomous Error Analysis and Correction
by: Xu, Tianlong, et al.
Published: (2024)

SkillBrew: Multi-Objective Curation of Skill Banks for LLM Agents
by: Hu, Wentao, et al.
Published: (2026)

RealGeneral: Unifying Visual Generation via Temporal In-Context Learning with Video Models
by: Lin, Yijing, et al.
Published: (2025)

DINORANKCLIP: DINOv3 Distillation and Injection for Vision-Language Pretraining with High-Order Ranking Consistency
by: Jiang, Shuyang, et al.
Published: (2026)

SafeSeek: Universal Attribution of Safety Circuits in Language Models
by: Yu, Miao, et al.
Published: (2026)

SVLTA: Benchmarking Vision-Language Temporal Alignment via Synthetic Video Situation
by: Du, Hao, et al.
Published: (2025)

Tracing the Arrow of Time: Diagnosing Temporal Information Flow in Video-LLMs
by: Han, Peitao, et al.
Published: (2026)

VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification
by: Meng, Jiahao, et al.
Published: (2026)

SIN-Bench: Tracing Native Evidence Chains in Long-Context Multimodal Scientific Interleaved Literature
by: Ren, Yiming, et al.
Published: (2026)

Improve Temporal Awareness of LLMs for Sequential Recommendation
by: Chu, Zhendong, et al.
Published: (2024)

From Macro to Micro: Probing Dataset Diversity in Language Model Fine-Tuning
by: Li, Haoyu, et al.
Published: (2025)

A Syllogistic Probe: Tracing the Evolution of Logic Reasoning in Large Language Models
by: Zang, Zhengqing, et al.
Published: (2026)

VideoZoomer: Reinforcement-Learned Temporal Focusing for Long Video Reasoning
by: Ding, Yang, et al.
Published: (2025)

Predictive Monitoring with Strong Trace Prefixes
by: Ang, Zhendong, et al.
Published: (2024)

CogVLM2: Visual Language Models for Image and Video Understanding
by: Hong, Wenyi, et al.
Published: (2024)

Synthesizing Evidence: Data-Pooling as a Tool for Treatment Selection in Online Experiments
by: Peng, Zhenkang, et al.
Published: (2025)

Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning
by: Yan, Yibo, et al.
Published: (2025)

Data and code for "Probing a minimal Kitaev chain with gate reflectometry"
by: Zhang, Yining
Published: (2025)

Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization
by: Jin, Yang, et al.
Published: (2024)

ARM2: Adaptive Reasoning Model with Vision Understanding and Executable Code
by: Xie, Jian, et al.
Published: (2025)

Direct Acquisition Optimization for Low-Budget Active Learning
by: Zhao, Zhuokai, et al.
Published: (2024)

RELAX: Reinforcement Learning Enabled 2D-LiDAR Autonomous System for Parsimonious UAVs
by: Wu, Guanlin, et al.
Published: (2023)

Self-Evolving Multi-Agent Systems via Decentralized Memory
by: Hao, Guangya, et al.
Published: (2026)

DynST: Dynamic Sparse Training for Resource-Constrained Spatio-Temporal Forecasting
by: Wu, Hao, et al.
Published: (2024)

VT-LVLM-AR: A Video-Temporal Large Vision-Language Model Adapter for Fine-Grained Action Recognition in Long-Term Videos
by: Li, Kaining, et al.
Published: (2025)

Is urban innovation capacity shaping new models of economic development? Evidence from the circular economy
by: Pengyu Chen, et al.
Published: (2024)

Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events
by: Liu, Xiaolin, et al.
Published: (2026)

PiTe: Pixel-Temporal Alignment for Large Video-Language Model
by: Liu, Yang, et al.
Published: (2024)

Temporal Evidence Routing with Structured Visual Evidence for TimeLogicQA
by: Sun, Yuyang, et al.
Published: (2026)