AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Seeing Isn't Orienting: A Cognitively Grounded Hierarchical Benchmark for Object Orientation in MLLMs

Nazia Tasnim, Keanu Nichols, Yuting Yan, Nicholas Ikechukwu, Elva Zou, Deepti Ghadiyaram, Bryan Plummer

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Spatial reasoning in VLMs

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
use token-based fusion instead of linear projection (ablation)Qwen2.5-3B-Inst. LoRA · DORI (LoRA fusion comparison)average coarse accuracy (%): 41.2 -> 74.3Improved
use token-based fusion instead of linear projection (ablation)Qwen2.5-3B-Inst. LoRA · DORI (LoRA fusion comparison)average granular accuracy (%): 19.1 -> 46.6Improved
add bottleneck to linear projection (ablation)Qwen2.5-3B-Inst. LoRA · DORI (LoRA fusion comparison)average coarse accuracy (%): 41.2 -> 32.1Hurt
LoRA finetune on DORIQwen2.5-3B-Inst. · DORI held-out split (LoRA finetuning)average coarse accuracy (%): 39.6 -> 79.5Improved
LoRA finetune on DORIQwen2.5-3B-Inst. · DORI held-out split (LoRA finetuning)average granular accuracy (%): 16.6 -> 50.2Improved
LoRA finetune on DORIQwen2.5-VL-3B · SAT (zero-shot)accuracy (%): 51.3 -> 63.3Improved
LoRA finetune on DORIQwen2.5-VL-3B · Blink Visual-Correspondence (zero-shot)accuracy (%): 25.3 -> 26.5No clear effect
add structured prompt (task description, examples, steps) (ablation)LLaVA-Next-8B · DORI View Parallelism granularaccuracy: 93% relative decline without structureImproved
add structured prompt (ablation)Mantis-Idfs-8B · DORI Compound Rotation coarseaccuracy: 141% relative surge without structureHurt
add structured prompt (ablation)DS-7B-Chat · DORI Inter-Object Direction coarse and Compound Rotation coarseaccuracy: 145% relative gain and 97% collapse without structureMixed
use instruction-tuned DeepSeek-7B-Chat instead of BaseDeepSeek-7B · DORI (full)average coarse accuracy (%): 23.1 -> 33.9Improved
upgrade Qwen2.5-3B to Qwen3-8BQwen family · DORI (full)average coarse accuracy (%): 35.0 -> 49.3Improved

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