Showing papers from School of Engineering and Applied Sciences, Harvard University Show all papers
Atlanta Poster Session 3, Thu, Dec 10, 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.
AI GameStore proposes evaluating general intelligence via scalable synthesis of human games, finding frontier vision-language models score under 10% of human averages on most generated games.
Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026 · ▲ 9 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.
Temporal Backtracking Search improves video reasoning by searching over the temporal axis and restarting from verified prefixes rather than resampling from scratch, achieving 22.7% versus 0.7% best-of-N out-of-distribution.
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.
A decentralized agent economy using auctions and economic selection emerges multi-step reasoning and outperforms monolithic baselines without centralized coordination.
Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026 · ▲ 10 on Hugging Face · Code ★ 59
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.
Out-of-distribution shifts rotate active subspaces, misaligning dictionary explainers; a geometry-adaptive realignment using unlabeled OOD activations closes the faithfulness gap and restores causal interpretability without training.
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.
LiFT generates high-resolution 3D medical images via inter-slice feature trajectories, achieving strong coherence with much lower inference cost.
Atlanta Poster Session 1, Wed, Dec 9, 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.
A hierarchical sparse autoencoder architecture explicitly models semantic concept hierarchies, improving reconstruction, interpretability, and efficiency in language model representations.
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.