Good Papers

Showing papers from DFKI & Max Planck Research School for Intelligent Systems Show all papers

80%Must read
?Must readVote to see the score
NeurIPS 2026U ArkansasU Arkansas - FayettevilleGoogle ResearchU LiverpoolDFKI & Max Planck Research SVision-language models

OmniSpace: Efficient Geometry Awareness for Autonomous Vehicles MLLMs

OmniSpace improves autonomous vehicle MLLM spatial reasoning via camera pose injection, multi-view epipolar attention, and 3D geometric distillation without auxiliary 3D models, surpassing existing methods across planning, risk detection, and language benchmarks.

Anh Hao Vo, Phu Loc Nguyen, Khoa Vo, Sieu Tran and 6 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it
lenient 5/5
medium 7/10
strict 0/5
91%Must read
?Must readVote to see the score
NeurIPS 2026U ArkansasU Arkansas - FayettevilleGoogle ResearchU LiverpoolDFKI & Max Planck Research SVision-language models

DriveSpatial: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving

DriveSpatial benchmarks vision-language models' spatiotemporal autonomous driving intelligence, finding a 28.4-point human gap with cognitive scene construction as the key bottleneck.

Anh Hao Vo, Khoa Vo, Phu Loc Nguyen, Sieu Tran and 9 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
18/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 18 of 20 reviewers recommend it
lenient 5/5
medium 10/10
strict 3/5
86%Must read
?Must readVote to see the score
NeurIPS 2026Hanoi University of Science and DeakinDFKI & Max Planck Research SVinUniversityMonashAI oversight & deception

BSO: Safety Alignment Is Density Ratio Matching

BSO recasts safety alignment as density ratio matching via Bregman divergence minimization, yielding a single-stage loss that improves the safety-helpfulness trade-off without auxiliary models.

Tien-Phat Nguyen, Truong Nguyen, Thin Nguyen, Duy M. H. Nguyen and 2 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
14/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 14 of 20 reviewers recommend it
lenient 4/5
medium 8/10
strict 2/5