Pith. sign in

REVIEW 10 cited by

Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.07973 v1 pith:Y3SDCMFM submitted 2024-04-11 cs.CV

classification cs.CV
keywords visualferretferret-v2groundingmodelreferringadditionalalignment
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

While Ferret seamlessly integrates regional understanding into the Large Language Model (LLM) to facilitate its referring and grounding capability, it poses certain limitations: constrained by the pre-trained fixed visual encoder and failed to perform well on broader tasks. In this work, we unveil Ferret-v2, a significant upgrade to Ferret, with three key designs. (1) Any resolution grounding and referring: A flexible approach that effortlessly handles higher image resolution, improving the model's ability to process and understand images in greater detail. (2) Multi-granularity visual encoding: By integrating the additional DINOv2 encoder, the model learns better and diverse underlying contexts for global and fine-grained visual information. (3) A three-stage training paradigm: Besides image-caption alignment, an additional stage is proposed for high-resolution dense alignment before the final instruction tuning. Experiments show that Ferret-v2 provides substantial improvements over Ferret and other state-of-the-art methods, thanks to its high-resolution scaling and fine-grained visual processing.

Discussion (0). Sign in to comment.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Actor as Its Own Critic: Unifying Region Understanding and Localization via CycleGRPO

    cs.CV 2026-07 accept novelty 7.0 of 10

    A single MLLM jointly improves region captioning and localization by rewarding captions that let it reconstruct the original mask, needing only region inputs.

  2. SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing

    cs.CV 2025-06 conditional novelty 7.0 of 10

    SAVVY-Bench tests audio-visual LLMs on dynamic 3D spatial questions, and the SAVVY pipeline, combining visual tracks with spatial audio and global mapping, lifts Gemini-2.5-pro accuracy from 50.9% to 58.0%.

  3. Teaching MLLMs to Say No: Generalized Referring Expression Comprehension via Refusal Calibrated GRPO

    cs.CV 2026-08 conditional novelty 6.0 of 10

    A recalibrated GRPO reinforcement learning method lets multimodal LLMs say 'None' for nonexistent referring expressions without sacrificing localization accuracy on objects that do exist.

  4. CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement

    cs.CV 2026-08 conditional novelty 6.0 of 10

    A chest X-ray VLM co-trained with classification and grounding heads, tuned with DAPO reinforcement learning, and augmented with deterministic measurement tools outperforms prior radiology VLMs on report generation, V...

  5. Strefer: Empowering Video LLMs with Space-Time Referring and Reasoning via Synthetic Instruction Data

    cs.CV 2025-09 conditional novelty 6.0 of 10

    Adding Strefer's synthetic space-time reference questions to video instruction tuning improves mask-referred description/QA, timestamp QA, and temporal reasoning over a video-LLM baseline.

  6. Region-Level Context-Aware Multimodal Understanding

    cs.CV 2025-08 conditional novelty 6.0 of 10

    Region-level context-aware instruction tuning with a large synthetic dataset improves MLLMs' ability to connect objects in images to their textual descriptions.

  7. Mitigating Object Hallucination via Robust Local Perception Search

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A training-free decoding method that uses an MLLM's own local object descriptions as a reward prior, combined with CLIP similarity, to cut object hallucination, especially under adversarial image noise.

  8. Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Training a multimodal LLM on GPT-4o-generated chain-of-thought referring traces, then optimizing with GRPO, improves referring accuracy and abstention on HumanRef.

  9. Qwen-Audio-VAE Technical Report

    eess.AS 2026-07 conditional novelty 5.0 of 10

    A 12.5 Hz continuous audio VAE reconstructs speech, music, and sound well while encoding 64×30s clips in 541 ms after latency-aware encoder pruning.

  10. Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos

    cs.CV 2025-06 reject novelty 5.0 of 10

    PAM extends SAM 2 with a frozen LLM and a Semantic Perceiver to jointly segment and describe regions in images, videos, and streaming video, and contributes a 0.6M-sample region-level streaming video caption dataset.

Pith tools