Conference
Open access
2026
,
Qin-Tong Zhang, Xin Lv, Jia-Long Wu et al.
· Proceedings of the 2026 Conf... · 1 citation
· ⚡1
Save
{ copied = true; setTimeout(() => copied = false, 1500) })"
class="icon-btn" aria-label="Copy link">
{ copied = 'apa'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy APA
Copied ✓
{ copied = 'mla'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy MLA
Copied ✓
{ copied = 'bibtex'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy BibTeX
Copied ✓
Across reasoning, long-context understanding, and agentic tasks, SAS consistently outperforms trainable sparse attention baselines across attention budgets, with especially large gains under tight budgets, demonstrating more effective context ranking for downstream tasks.
Zhi-Wei Li, Lei Zhu, Hao Gu et al.
· 1 citation
Save
{ copied = true; setTimeout(() => copied = false, 1500) })"
class="icon-btn" aria-label="Copy link">
{ copied = 'apa'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy APA
Copied ✓
{ copied = 'mla'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy MLA
Copied ✓
{ copied = 'bibtex'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy BibTeX
Copied ✓
FlowBalance, a verifier-grounded self-improvement method that learns a normalized distribution over complete responses, improves average performance over FlowRL on both Qwen3-4B and Qwen3-8B, while also improving training speed and stability, avoiding direct OPSD's response-length collapse, and exhibiting higher correc...
Zi-Xun Huang, Kishan Panaganti, Hai-Tao Mi et al.
· 0 citations
Save
{ copied = true; setTimeout(() => copied = false, 1500) })"
class="icon-btn" aria-label="Copy link">
{ copied = 'apa'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy APA
Copied ✓
{ copied = 'mla'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy MLA
Copied ✓
{ copied = 'bibtex'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy BibTeX
Copied ✓