Multimodal

Blog Multimodal

DataComp-VLM: Improved Open Datasets for Vision-Language Models

arXiv:2606.28551v1 Announce Type: new Abstract: Building performant Vision-Language Models (VLMs) requires carefully curating large-scale training datasets, yet the community lacks systematic benchmarks for evaluating such curation strategies. We introduce DataComp for VLMs (DCVLM), a benchmark for controlled data-centric experiments to improve VLM training. As part of DCVLM, we collect 160 datasets spanning four data types -- image-caption pairs, multimodal interleaved documents, text-only, and...

30.06.2026

Modelo LLMs & Texto

yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2

Modelo de geração de texto · 12 B de parâmetros — 1.8 mil downloads e 47 curtidas no Hugging Face.

30.06.2026 ·↓ 1833

Modelo Multimodal

Jackrong/Qwopus3.6-35B-A3B-Coder-MTP-GGUF

Modelo de visão e linguagem · 35 B de parâmetros · MoE — 290.9 mil downloads e 172 curtidas no Hugging Face.

30.06.2026 ·↓ 290863

Paper LLMs & Texto

GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity

Three seemingly distinct training methods for language models are shown to be variations of a single approach based on standard deviation adjustment, with the disagreement among sa…

30.06.2026 ·▲ 6

Paper LLMs & Texto

Xiaomi-GUI-0 Technical Report

A native multimodal GUI agent trained in real-device environments demonstrates superior performance and stability compared to traditional benchmark-based approaches.

30.06.2026 ·▲ 8

Paper LLMs & Texto

Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning

A reinforcement learning approach called MRPO is introduced to improve clinical image reasoning by addressing cascading errors through step-wise process rewards, demonstrating supe…

30.06.2026 ·▲ 20

Paper LLMs & Texto

Seeing Is Not Sharing: Some Vision-Language Models Overestimate Common Ground in Asymmetric Dialogue

Vision-language models struggle to distinguish between shared and interpreted visual information in dialogue, relying on static map cues rather than dynamic grounding processes.

30.06.2026 ·▲ 6

Blog LLMs & Texto

DMV-Bench: Diagnosing Long-Horizon Multimodal Agents' Visual Memory with Incidental Cue Injection

arXiv:2606.27499v1 Announce Type: new Abstract: Research on agent memory has matured rapidly, but almost entirely on the text side: few existing benchmarks ask, in an interactive environment, when an agent genuinely needs to remember what it saw rather than what it could write down. We introduce DMV-Bench (Code: https://github.com/yyyujintang/DMV-Bench), the first interactive benchmark for multimodal-agent visual memory. DMV-Bench is built on a controlled home-furnishing e-commerce catalogue of ...

29.06.2026

Blog LLMs & Texto

JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications

arXiv:2606.28070v2 Announce Type: new Abstract: JD$.$com, one of the world's largest e-commerce platforms, serves over 700 million active users and millions of merchants, with a catalog of tens of billions of SKUs. At this scale, high-quality, structured item knowledge underpins a better consumer experience, lower management costs, and higher operational efficiency-yet producing and serving it poses three industrial-scale challenges: fast-emerging concepts, high-quality knowledge production for ...

29.06.2026

Blog Áudio & Voz

A Survey of Automated Presentation Coaching: Systems, Methods, and Open Challenges

arXiv:2606.27380v1 Announce Type: new Abstract: Automated coaching for oral presentations sits at the intersection of computer-assisted pronunciation training (CAPT), prosody modeling, and speech synthesis, yet no prior work has systematically surveyed and compared existing systems along these dimensions. This survey reviews and categorizes automated presentation coaching systems, spanning pronunciation tutors, fluency and prosody coaches, multimodal trainers, and conference Q&A practice tools. ...

29.06.2026

Blog Multimodal

DeLux: Cross-Modal Local Artifact Restoration in Video Using Neuromorphic Data

arXiv:2606.27576v1 Announce Type: new Abstract: Conventional RGB cameras suffer from lighting artifacts such as flare, glare, flicker, and overexposure, leading to irrecoverable information loss that necessitates computational restoration. However, existing approaches treat these problems in isolation, failing to recover structural details completely obscured by complex spatially discrete image degradations. In this paper, we propose a novel cross-modal restoration paradigm and present DeLux, a ...

29.06.2026

Blog LLMs & Texto

MER-R1: Multimodal Emotion Reasoning via Slow-Fast Thinking Synergy

arXiv:2606.27652v1 Announce Type: new Abstract: We find that explicit reasoning does not necessarily translate into better multimodal emotion recognition (MER) accuracy, even though it makes predictions more interpretable. Specifically, for reasoning-based MLLMs, fast thinking by triggering direct answers often outperforms slow thinking after deliberative reasoning. Our empirical analyses show that fast thinking improves recall with broader and more confident predictions, whereas slow thinking f...

29.06.2026