Showing papers from UC Davis Show all papers
Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026
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.
VideoRLVR applies reinforcement learning with verifiable rewards to video diffusion models, improving rule-consistent visual reasoning and cutting training latency 40% via early-step optimization.
Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026 · ▲ 9 on Hugging Face · Code ★ 28
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.
Test-time alignment via million-parameter factorized ranking models exploits massive headroom for personalized generation, outperforming billion-parameter reward models with minimal overhead.
Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 11 on Hugging Face
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.
Multimodal LLMs suffer spurious cross-modality interference that distorts decisions, and a unified finetuning framework with perturbation augmentation and consistency regularization improves robustness and generalization.
Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 1 on Hugging Face · Code ★ 8
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.
Linear self-attention transformers provably implement in-context policy-improvement via explicit constructions, with gradient flow converging exponentially to optimal RL update parameters under distribution richness conditions.
Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026
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.
ModelLens learns a latent space over model-dataset-metric tuples from noisy leaderboard data to rank unseen models on unseen datasets without target evaluation, improving routing by up to 81%.
Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 14 on Hugging Face · Code ★ 130
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.