DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models (2025 · 21 citations)
Large Reasoning Models tend to "overthink": they produce very long chains of thought full of redundant checks and backtracking, which wastes compute.
Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation (2026 · 13 citations)
Small LLMs are usually distilled by fine-tuning them on outputs from the most powerful available teacher. Prior work shows this can backfire: very strong teachers may produce answers that are too complex or too far from what the student can absorb. Earlier remedies (Mix, CAR) still make every candidate teacher answer…
Beyond Math: Stories as a Testbed for Memorization-Constrained Reasoning in LLMs (2026 · 10 citations)
Research on memorization in LLMs has mostly focused on math and logic, where recalling previously seen problems is treated as a pure shortcut.
From Recognition to Reasoning: Benchmarking and Enhancing MLLMs on Real-World Receipt Document Understanding (2026)
The paper addresses Visual Information Extraction (VIE) from receipts and invoices. Existing benchmarks are small, synthetic, or limited to narrow domains, and they mostly test literal text extraction. The authors introduce ReceiptBench, a human-annotated collection of 10,656 real-world financial documents, including…

Co-authors here

12 of 14 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 39 times (of the 149,439 papers whose bibliographies we read); 11 citing papers with a page here →.

Updated 1 November 2026