VFig lands NeurIPS 2026: 4B VLM matches GPT-5.2 at converting complex figures to SVG
jmin__cho · x · 2026-09-30
VFig, a VLM that vectorizes complex figures into editable SVG, is accepted to the NeurIPS 2026 E&D track.
- Targets the pain of seeing a great Figure 1 in a paper but not being able to edit and adapt it: VFig converts any diagram, simple or complex, into clean, editable SVG code
- Built on Qwen3-VL 4B with SFT and RL
- Matches GPT-5.2's performance on converting complex diagrams to SVG and outperforms open-source generalists and specialists across simple-to-complex vectorization
- A live demo is available
More from Research
- Claude sets NIST circuit record: AES S-Box in 28 AND-gates, 131 total — jedisct1 · 2026-09-30
- Not every model failure is lack of capability: Terminal-Bench evals hide safety declines — abeirami · 2026-09-30
- NVIDIA's Physis-Lang puts physics reasoning in captions, tops Physics-IQ with Cosmos 3 — NVIDIAAI · 2026-09-30
- Laser on a 3D printer turns Kapton tape into laser-induced graphene with PWM control — johnowhitaker · 2026-09-30
- COLM paper: narrative choices alone give AI fiction away, even without AI-speak — MohitIyyer · 2026-09-30
- CMU Study Examines How Content Creators Responsibly Use Generative AI Tools — steph_milani · 2026-09-30