Showing papers from GIST Show all papers
Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · 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.
ComPose tracks 6DoF object pose in RGB video by using hand motions as complementary cues, achieving robust accuracy under severe occlusion without external priors.
Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · 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.
Diagonal regularizers saturate at a prior-driven power law because isotropic truncation noise and eigenvalue counting yield flat loss landscapes, so learned diagonal forms barely beat the closed form and only cross-mode coupling enables real gains.
Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · 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.
A reasoning-prefix masking framework distills think-answer visual reasoning into compact VLMs by masking salient reasoning cues to force visual anchoring, improving multimodal benchmarks over prior distillation methods.
Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · 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.
DyMoS rebalances reference-frame self-attention in image-to-video models to boost motion dynamics without retraining or altering inputs.
Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · 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.
Random soft prompt injection boosts LLM math reasoning by flattening early token distributions to diversify reasoning paths and widen Pass@N without any training.
Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · 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.