REVIEW 7 cited by
Groma: Localized Visual Tokenization for Grounding Multimodal 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
read the original abstract
We introduce Groma, a Multimodal Large Language Model (MLLM) with grounded and fine-grained visual perception ability. Beyond holistic image understanding, Groma is adept at region-level tasks such as region captioning and visual grounding. Such capabilities are built upon a localized visual tokenization mechanism, where an image input is decomposed into regions of interest and subsequently encoded into region tokens. By integrating region tokens into user instructions and model responses, we seamlessly enable Groma to understand user-specified region inputs and ground its textual output to images. Besides, to enhance the grounded chat ability of Groma, we curate a visually grounded instruction dataset by leveraging the powerful GPT-4V and visual prompting techniques. Compared with MLLMs that rely on the language model or external module for localization, Groma consistently demonstrates superior performances in standard referring and grounding benchmarks, highlighting the advantages of embedding localization into image tokenization. Project page: https://groma-mllm.github.io/.
Forward citations
Cited by 7 Pith papers
-
MentalThink: Shaping Thoughts in Mental SVG World
MLLMs that generate and render SVG sketches as multi-turn intermediate reasoning steps reach 55.1% on VSIBench and 76.0% on MindCube, far above the Qwen2.5-VL-7B backbone.
-
OmniSch: A Multimodal PCB Schematic Benchmark For Structured Diagram Visual Reasoning
OmniSch is the first benchmark exposing gaps in LMMs for PCB schematic visual grounding, topology-to-graph parsing, geometric weighting, and tool-augmented reasoning.
-
Teaching MLLMs to Say No: Generalized Referring Expression Comprehension via Refusal Calibrated GRPO
A recalibrated GRPO reinforcement learning method lets multimodal LLMs say 'None' for nonexistent referring expressions without sacrificing localization accuracy on objects that do exist.
-
ReferTrack: Referring Then Tracking for Embodied Visual Tracking
A refer-then-track policy picks the target from indexed detections before planning waypoints, achieving state-of-the-art single-view results on EVT-Bench and approaching multi-camera performance.
-
Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning
Training a multimodal LLM on GPT-4o-generated chain-of-thought referring traces, then optimizing with GRPO, improves referring accuracy and abstention on HumanRef.
-
Chain-of-Talkers (CoTalk): Fast Human Annotation of Dense Image Captions
Chain-of-Talkers (CoTalk) has annotators sequentially dictate only the missing visual details, and it reports modest gains in annotation speed and caption density over parallel typed annotation.
-
Region-Aware Multimodal Large Language Model via SlowFast Tokenization and Pseudo-Mask Guidance for 3D CT Report Generation
MedRegion-CT integrates region-representative tokens, mask-driven segmentation tokens, and patient-specific attribute prompts into a multimodal LLM, reporting state-of-the-art scores on RadGenome-Chest CT report generation.
Discussion (0). Sign in to comment.