#MLLM
LightNews LightNews
arxiv-cs-cv.bsky.social
Zhenchen Tang, Songlin Yang, Bo Peng, Zichuan Wang, Jing Dong
Revisiting MLLM Based Image Quality Assessment: Errors and Remedy
https://arxiv.org/abs/2511.07812
November 12, 2025 at 10:36 AM
cslg-bot.bsky.social
Xu, Yang, Zhao, Zhang, Chen, Ma, Hou, Wu, Li, Hu, Guan, Li, Po: From Exploration to Exploitation: A Two-Stage Entropy RLVR Approach for Noise-Tolerant MLLM Training https://arxiv.org/abs/2511.07738 https://arxiv.org/pdf/2511.07738 https://arxiv.org/html/2511.07738
November 12, 2025 at 6:33 AM
cscv-bot.bsky.social
Zhenchen Tang, Songlin Yang, Bo Peng, Zichuan Wang, Jing Dong: Revisiting MLLM Based Image Quality Assessment: Errors and Remedy https://arxiv.org/abs/2511.07812 https://arxiv.org/pdf/2511.07812 https://arxiv.org/html/2511.07812
November 12, 2025 at 6:30 AM
researchtrend.ai
[2025-11-11] 📚 Updates in #MLLM

(1) <a href="https://researchtrend.ai/papers/2511.06651" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link" target="_blank" rel="noopener" data-link="bsky">NOVO: Bridging LLaVA and SAM with Visual-only Prompts for Reasoning Segmentation
(2) NOVO: Bridging LLaVA and SAM with Visual-only Prompts for Reasoning Segmentation

🔍 More at researchtrend.ai/communities/MLLM
November 11, 2025 at 4:02 AM
nickaesp.com
Why AI Sucks At Telling Time... and why this should concern us for autonomous vehicles and more.

#News #TechNews #AI #MLLM #AIlimitations #SelfDriving #MedTech
Why AI Sucks At Telling Time...
YouTube video by Nick Espinosa
youtu.be
November 10, 2025 at 10:10 PM
nickaesp.com
Daily podcast: Why AI Sucks At Telling Time... and why this should concern us for autonomous vehicles and more.

#News #TechNews #AI #MLLM #AIlimitations #SelfDriving #MedTech #podcast

soundcloud.com/nickaesp/acr
Why AI Sucks At Telling Time...
and why this should concern us for autonomous vehicles and more.
soundcloud.com
November 10, 2025 at 10:09 PM
researchtrend.ai
[2025-11-10] 📚 Updates in #MLLM

(1) Towards Explainable Fake Image Detection with Multi-Modal Large Language Models

🔍 More at researchtrend.ai/communities/MLLM
November 10, 2025 at 6:48 AM
researchtrend.ai
[2025-11-07] 📚 Updates in #MLLM

(1) <a href="https://researchtrend.ai/papers/2410.04514" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link" target="_blank" rel="noopener" data-link="bsky">DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination
(2) DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination

🔍 More at researchtrend.ai/communities/MLLM
November 7, 2025 at 3:08 AM
csmm-bot.bsky.social
Liu, \c{C}oban, Schevchenko, Tang, Zhu, Mandel, Devaney: An Evaluation of Interleaved Instruction Tuning on Semantic Reasoning Performance in an Audio MLLM https://arxiv.org/abs/2511.02234 https://arxiv.org/pdf/2511.02234 https://arxiv.org/html/2511.02234
November 5, 2025 at 6:33 AM
researchtrend.ai
[2025-11-05] 📚 Updates in #AuLLM

(1) <a href="https://researchtrend.ai/papers/2511.02234" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link" target="_blank" rel="noopener" data-link="bsky">An Evaluation of Interleaved Instruction Tuning on Semantic Reasoning Performance in an Audio MLLM
(2) An Evaluation of Interleaved Instruction Tuning on Semantic Reasoning Performance in an Audio MLLM

🔍 More at researchtrend.ai/communities/AuLLM
November 5, 2025 at 3:10 AM
researchtrend.ai
[2025-11-05] 📚 Updates in #MLLM

(1) <a href="https://researchtrend.ai/papers/2511.02607" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link" target="_blank" rel="noopener" data-link="bsky">UniChange: Unifying Change Detection with Multimodal Large Language Model
(2) UniChange: Unifying Change Detection with Multimodal Large Language Model

🔍 More at researchtrend.ai/communities/MLLM
November 5, 2025 at 3:10 AM
cslg-bot.bsky.social
Zhicheng Wang, Chen Ju, Xu Chen, Shuai Xiao, Jinsong Lan, Xiaoyong Zhu, Ying Chen, Zhiguo Cao: Explore More, Learn Better: Parallel MLLM Embeddings under Mutual Information Minimization https://arxiv.org/abs/2511.01588 https://arxiv.org/pdf/2511.01588 https://arxiv.org/html/2511.01588
November 4, 2025 at 6:35 AM
researchtrend.ai
[2025-11-04] 📚 Updates in #MLLM

(1) <a href="https://researchtrend.ai/papers/2511.00279" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link" target="_blank" rel="noopener" data-link="bsky">LongCat-Flash-Omni Technical Report
(2) LongCat-Flash-Omni Technical Report
(3) UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings

🔍 More at researchtrend.ai/communities/MLLM
November 4, 2025 at 4:01 AM
csai-bot.bsky.social
Zhan, Ha, Yang, Xu, Chen, Gui, Wang, Zhang, Ji, Kang: Visual Backdoor Attacks on MLLM Embodied Decision Making via Contrastive Trigger Learning https://arxiv.org/abs/2510.27623 https://arxiv.org/pdf/2510.27623 https://arxiv.org/html/2510.27623
November 3, 2025 at 6:29 AM
researchtrend.ai
[2025-11-03] 📚 Updates in #MLLM

(1) <a href="https://researchtrend.ai/papers/2510.27164" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link" target="_blank" rel="noopener" data-link="bsky">Generating Accurate and Detailed Captions for High-Resolution Images
(2) Generating Accurate and Detailed Captions for High-Resolution Images

🔍 More at researchtrend.ai/communities/MLLM
November 3, 2025 at 3:08 AM
researchtrend.ai
[2025-10-31] 📚 Updates in #MLLM

(1) PairUni: Pairwise Training for Unified Multimodal Language Models
(2) <a href="https://researchtrend.ai/papers/2510.26583" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link" target="_blank" rel="noopener" data-link="bsky">Emu3.5: Native Multimodal Models are World Learners
(3) Emu3.5: Native Multimodal Models are World Learners

🔍 More at researchtrend.ai/communities/MLLM
October 31, 2025 at 3:10 AM
themanburglar.bsky.social
LLM? MLM?? MLLM??? WLW??????? some of you need to be Loving the Lord More, More Lord More, More Loving the Lord Mas, and Worshiping the Lord in Wonder
October 30, 2025 at 3:10 PM
arxiv-cs-cv.bsky.social
Ruiyang Zhang, Jiahao Luo, Xiaoru Feng, Qiufan Pang, Yaodong Yang, Juntao Dai
SafeEditor: Unified MLLM for Efficient Post-hoc T2I Safety Editing
https://arxiv.org/abs/2510.24820
October 30, 2025 at 8:14 AM
cscv-bot.bsky.social
Ruiyang Zhang, Jiahao Luo, Xiaoru Feng, Qiufan Pang, Yaodong Yang, Juntao Dai: SafeEditor: Unified MLLM for Efficient Post-hoc T2I Safety Editing https://arxiv.org/abs/2510.24820 https://arxiv.org/pdf/2510.24820 https://arxiv.org/html/2510.24820
October 30, 2025 at 6:30 AM
researchtrend.ai
[2025-10-30] 📚 Updates in #MLLM

(1) Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation
(2) PairUni: Pairwise Training for Unified Multimodal Language Models

🔍 More at researchtrend.ai/communities/MLLM
October 30, 2025 at 3:08 AM
researchtrend.ai
[2025-10-29] 📚 Updates in #MLLM

(1) <a href="https://researchtrend.ai/papers/2510.23642" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link" target="_blank" rel="noopener" data-link="bsky">VisCoder2: Building Multi-Language Visualization Coding Agents
(2) VisCoder2: Building Multi-Language Visualization Coding Agents
(3) Compositional Image Synthesis with Inference-Time Scaling

🔍 More at researchtrend.ai/communities/MLLM
October 29, 2025 at 3:09 AM
arxiv-cs-cv.bsky.social
Zahraa Al Sahili, Maryam Fetanat, Maimuna Nowaz, Ioannis Patras, Matthew Purver
FairJudge: MLLM Judging for Social Attributes and Prompt Image Alignment
https://arxiv.org/abs/2510.22827
October 28, 2025 at 10:58 AM
cscv-bot.bsky.social
Zahraa Al Sahili, Maryam Fetanat, Maimuna Nowaz, Ioannis Patras, Matthew Purver: FairJudge: MLLM Judging for Social Attributes and Prompt Image Alignment https://arxiv.org/abs/2510.22827 https://arxiv.org/pdf/2510.22827 https://arxiv.org/html/2510.22827
October 28, 2025 at 6:32 AM
researchtrend.ai
[2025-10-28] 📚 Updates in #MLLM

(1) <a href="https://researchtrend.ai/papers/2510.21794" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link" target="_blank" rel="noopener" data-link="bsky">Token-Level Inference-Time Alignment for Vision-Language Models
(2) Token-Level Inference-Time Alignment for Vision-Language Models
(3) Top-Down Semantic Refinement for Image Captioning

🔍 More at researchtrend.ai/communities/MLLM
October 28, 2025 at 3:13 AM
cscr-bot.bsky.social
Xingwei Zhong, Kar Wai Fok, Vrizlynn L. L. Thing: Enhanced MLLM Black-Box Jailbreaking Attacks and Defenses https://arxiv.org/abs/2510.21214 https://arxiv.org/pdf/2510.21214 https://arxiv.org/html/2510.21214
October 27, 2025 at 6:30 AM