Showing papers from Hohai University 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.
TACO is a training-free framework that learns adaptive compression rules from terminal agent trajectories to filter noisy observations, improving accuracy by 1-4% and reducing token usage across benchmarks.
Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 24 on Hugging Face · Code ★ 47
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.
JMed48k introduces a Japanese medical licensing benchmark with 48,862 questions showing proprietary vision-language models gain substantially from images while medical-specific systems ignore visual evidence.
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.
EcoGym benchmarks long-horizon LLM economic planning across open-source environments, revealing no single model dominates and exposing strategic and execution suboptimalities.
Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 11 on Hugging Face · Code ★ 99
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.