Showing papers from Toyota Research Institute Show all papers
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.
Alem benchmarks open-ended multi-agent coordination for language agents, showing frontier LLMs average ~6% returns and individual competence does not imply coordination competence.
Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 7 on Hugging Face · Code ★ 51
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.
Enforcing multi-step latent predictions improves context-based offline meta-RL by capturing task dynamics, reducing value errors, and boosting zero-shot and few-shot generalization.
Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · 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.
Analytical Bias Correction fixes O(1/n) minibatch centroid bias in drifting models via a closed-form plug-in, reducing it to O(1/n²) with negligible overhead and improving CIFAR-10 FID.
Atlanta Poster Session 2, Wed, Dec 9, 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.
EyeVLM benchmarks vision-language models on gaze following and social gaze prediction, finding they lack precise gaze understanding despite training improvements.
Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · 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.