AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

HAMMER: Harnessing MLLMs via Cross-Modal Integration for Intention-Driven 3D Affordance Grounding

Lei Yao, Yong Chen, Yuejiao Su, Yi Wang, Moyun Liu, Lap-Pui Chau

CVPR 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Region-level vision-language alignment

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add object category to the prompt and predict affordance label as auxiliary output (ablation)HAMMER · PIAD UnseenaIOU (%): 8.78 -> 13.71Improved
add object category to the prompt (ablation)HAMMER · PIAD UnseenaIOU (%): 12.35 -> 13.71Improved
add hierarchical cross-modal integration (ablation)HAMMER · PIAD UnseenaIOU (%): 10.50 -> 13.71Improved
add multi-granular geometry lifting (ablation)HAMMER · PIAD UnseenaIOU (%): 10.20 -> 13.71Improved
add both integration and geometry lifting (ablation)HAMMER · PIAD SeenaIOU (%): 19.55 -> 22.20Improved
add textual language modeling loss (ablation)HAMMER · PIAD UnseenaIOU (%): 9.78 -> 13.71Improved
use multi-granular lifting instead of single-stage lifting (ablation)HAMMER · PIAD UnseenaIOU (%): 12.26 -> 13.71Improved
use multi-granular lifting instead of concatenation lifting (ablation)HAMMER · PIAD UnseenaIOU (%): 11.45 -> 13.71Improved
fine-tune MLLM language component with LoRA instead of freezing (ablation)HAMMER · PIAD UnseenaIOU (%): 7.55 -> 13.71Improved
add Stage I (bottleneck cross-attention) of hierarchical integration (ablation)HAMMER · PIAD UnseenaIOU (%): 11.85 -> 13.71Improved
swap PointNet++ (from scratch) for pretrained Uni3D backbone (ablation)HAMMER · PIAD SeenaIOU (%): 22.20 -> 24.67 (seen); 13.71 -> 12.28 (unseen)Mixed
use Qwen2.5-VL as MLLM instead of segmentation-tuned LISA / LISA++ (ablation)HAMMER · PIAD UnseenaIOUImproved

Later papers that compared with this method

3 later accepted papers report HAMMER as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy