ExperiGen: Agentic Hypothesis Discovery from Observational Data

Jishu Sen Gupta, Harini S I, Somesh K Singh, Mohamad Tawseeq Syed and 5 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

ANCHOR: Audio-Visually Grounded Chain-of-Thought Reasoning Benchmark

Joel Julin, Souraja Kundu, Liza Dahiya, George Z Wei and 5 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Beyond Copy-Paste: How Well Do Subject-Driven Video Models Understand Their Subjects?

Zun Wang, Kenan Deng, Daniel Blackburn, Linlin Lu and 4 more

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Improved Baselines with Representation Autoencoders

Using summed last-k encoder layers and combining RAE with REPA, RAEv2 achieves state-of-the-art gFID of 1.06 in 80 epochs with 10x faster convergence and free guidance.

Jaskirat Singh, Boyang Zheng, Zongze Wu, Richard Zhang and 2 more

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

The Many Senses of Visual Similarity: A Text-Prompted Image Perceptual Metric

A dataset of multi-aspect human visual similarity judgments benchmarks vision-language models and yields the TPIPS metric, which aligns with human perception and enables text-guided image retrieval and generative evaluation.

Sheng-Yu Wang, Yotam Nitzan, Aaron Hertzmann, Jun-Yan Zhu and 3 more

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

LLM Judge Validation Under Sparse Overlap: From Inference to Design

Sparse overlap in LLM judge validation drives wrong deployment decisions, reaching 25% error at 5% overlap; minimum 25% overlap and stratified allocation reduce errors significantly.

Junxuan Li, Arko Mukherjee, Soumyabrata Pal

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

End-to-End Training for Unified Tokenization and Latent Denoising

UNITE unifies tokenization and latent diffusion via a shared generative encoder, enabling single-stage joint training from scratch without adversarial losses or pretrained encoders to reach near state-of-the-art FID scores.

Shivam Duggal, Xingjian Bai, Zongze Wu, Richard Zhang and 4 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026