lab NVIDIA Research · 15h ago · research

GenRecal distills large vision-language models to small ones via recalibration

from English

Researchers present GenRecal, a general-purpose distillation framework that transfers knowledge from large vision-language models (VLMs) to smaller, more efficient counterparts. The method addresses the challenge of heterogeneous VLM architectures by using a Recalibrator to align and adapt feature representations across different model types.

GenRecal enables effective knowledge transfer between VLMs built on different LLMs with varying token types, vocabulary sizes, and index orderings.
Extensive experiments on multiple challenging benchmarks show that GenRecal significantly improves baseline performances.
The distilled small models eventually outperform large-scale open- and closed-source VLMs.

This framework allows for the deployment of high-performance vision-language capabilities on resource-constrained devices by overcoming architectural limitations inherent in previous distillation methods.

Importance 1/3 Trust 3/3 NVIDIA Research Multimodal Research paper

Read original

lab Microsoft Research Blog · 4h ago · 1 view

Microsoft Research introduces CARE-X, a unified chest X-ray VLM with auxiliary supervision and tool-augmented measurement

Microsoft Research has introduced CARE-X, a research model designed to address gaps in current radiology vision-language models by combining generative report writing with calibrated diagnostic predictions. The system uses reinforcement learning (DAPO) to reward clinical correctness and pairs the Qwen3-VL-4B-Instruct model with deterministic measurement tools to evaluate performance on conditions requiring precise calculations.

lab NVIDIA Research · 15h ago

Hide to See introduces reasoning-prefix masking for VLM distillation

Researchers propose a novel think-answer distillation framework that improves compact vision-language models' ability to utilize visual evidence by masking salient reasoning prefixes. This approach addresses the "visual forgetting" issue common in long think-answer traces, where students lose focus on visual cues during extended reasoning.

arxiv arXiv cs.CL · 8d ago · 4 views

Douyin releases DME multimodal embedding model with state-of-the-art performance

Douyin has released the technical report for its Multimodal Embedding (DME) model, which combines large-scale contrastive pre-training with latent reasoning to achieve strong discrimination and efficiency.

media Hugging Face Forums · 10d ago · 1 view

High school student seeks arXiv endorser for AttnRoute-MoE Vision Transformer paper

Hanyu (Olivia) Yu, a high school sophomore, is seeking an arXiv endorser in cs.LG or cs.CV to upload her independent preprint titled "AttnRoute-MoE: Attention-Prior Routing for Mixture-of-Experts Vision Transformers."

arxiv arXiv cs.AI · 15d ago · 1 view

ClinFusion introduces vision-centric MLLM for holistic medical understanding

Researchers introduce ClinFusion, a vision-centric multimodal large language model designed to address the challenges of deploying AI in clinical practice by unifying 2D and 3D medical image understanding. The system features a compositional cascaded vision encoder with a Cascade Spatial-Aware Locality Fusion operator and includes a new evaluation framework comprising MedIF-Bench and region-of-interest-grounded metrics.