Showing papers from Xiaohongshu Show all papers
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.
Paris Poster Session 1, Wed, Dec 9, 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.
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.
Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 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.
Increasing rollouts fails in group-based RL because normalized gradients cancel; SALT adaptively reweights updates via subspace decomposition to recover effective learning.
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.
OASES co-trains a search policy and adaptive evaluator to provide outcome-aligned process rewards, outperforming RL baselines on multi-hop QA benchmarks.
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.
xHC expands Transformer hyper-connections beyond four streams via sparse updates and temporal augmentation, improving scaling efficiency. It boosts 18B MoE downstream scores by 4.0 points over mHC with lower compute and reduced memory traffic via xHC-Flash.
Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 54 on Hugging Face · Code ★ 68
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.
Hint Tuning calibrates reasoning depth by using an instruct model as a difficulty probe, cutting tokens by 24-66% with 1K samples.
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.
AEM adaptively modulates response-level entropy dynamics for supervision-free credit assignment in multi-turn agent RL, improving exploration-exploitation trade-offs and consistently boosting strong baselines across ALFWorld, WebShop, and SWE-bench-Verified.
Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 21 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.
Knowledge-graph paths provide intermediate supervision for self-evolving search agents, improving question validity via relational context and solver rewards via waypoint coverage, boosting multi-hop QA across benchmarks.
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.
Vision-OPD distills a crop-conditioned teacher into a full-image student via on-policy self-distillation to improve fine-grained visual understanding without external teachers or tools. It achieves competitive or superior performance on fine-grained benchmarks against larger open-source, closed-sour
Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 5 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.