activity
20242026
most citedOn the Rigour of Scientific Writing: Criteria, Analysis, and Insights

2 citations · 6 across the 13 of their papers we have counts for

collaborators
Showing 2026Show all

5 papers · 1 filter

cs.LG2026

When Tool-Backed Skill Retrieval Fails: Source-Style Collapse in Executable Capability Retrieval

Yiqi Liu, Joseph James, Yang Wang +2

Large-scale agents increasingly rely on retrieval to access external capabilities. We study this retrieval gate in structured tools and APIs, a measurable class of tool-backed exec…

cs.AI2026

Broken Symmetry in LLM Refusal: Answer Release Is More Local Than Refusal Restoration

Yiqi Liu, Yang Wang, Songxin Wang +2

When a language model refuses to answer a prompt, it is unclear whether the correct answer is erased from its internal representations, or merely suppressed at the output layer. We…

cs.CL2026

Reading Between the Frames: Interpreting Implicit and Non-literal Meaning in Social Media Videos

Yang Wang, Yanan Ma, Yiqi Liu +7

Social media videos often communicate meanings that go beyond their visible actions, captions, or speech. A mundane clip may become humorous, ironic, or satire only through the int…

cs.SD2026

The Achilles' Heel of Angular Margins: A Chebyshev Polynomial Fix for Speaker Verification

Yang Wang, Yiqi Liu, Chenghao Xiao +1

Angular margin losses, such as AAM-Softmax, have become the de facto in speaker and face verification. Their success hinges on directly manipulating the angle between features and…

cs.CL2026

RIGOURATE: Quantifying Scientific Exaggeration with Evidence-Aligned Claim Evaluation

Joseph James, Chenghao Xiao, Yucheng Li +2

Scientific rigour tends to be sidelined in favour of bold statements, leading authors to overstate claims beyond what their results support. We present RIGOURATE, a two-stage multi…