7 papers
ReTaCo: Residual-Target Control for On-Policy Distillation
Zixiang Ni, Zhuo Hu, Renjie Cao +8
On-policy distillation (OPD) trains a student on its own generated prefixes with token-level teacher feedback, but transmitting or storing the teacher's full-vocabulary distributio…
When Unpaired Sets Support Shared-Corruption Calibration: Moment Geometry and Two-Sample Precision
Shuheng Cao, Zhenhao Zhang, Ruiqi Chen +5
Collections of diverse observations often share one acquisition, processing, geometric, or channel corruption, while only an unpaired clean reference set is available. For a prescr…
RCShift: Certifying When Partial Linkage Suffices for Finite-Sample Decisions
Shuheng Cao, Ruiqi Chen, Zhenhao Zhang +5
Systems with costly gold outcomes and cheaper auxiliary observations must decide how much record linkage to retain. Complete pairing retains every joint counter, while separate mar…
CertBind from Multimodal Connectivity to Certifiable Retrieval Decisions
Shuheng Cao, Zhenhao Zhang, Ruiqi Chen +7
Lightweight connectors make frozen multimodal encoders composable at the representation level. Deployment exposes a second problem at the level of task decisions. A connected route…
Beyond Agreement: Scoring Panel-Surfaced Biomedical Entity Candidates for Curator Triage
Shuheng Cao, Ruiqi Chen, Renjie Cao +3
Biomedical NER is deceptively simple for modern LLMs: plausible biomedical mentions are easy to surface, but corpus-convention correctness depends on annotation conventions, span b…
Mira-Embeddings-V1: Domain-Adapted Semantic Reranking for Recruitment via LLM-Synthesized Data
Zhaohua Liang, Zhilin Wang, Renjie Cao +1
Candidate sourcing for recruiters is best viewed as a two-stage retrieval and reranking pipeline with recall as the primary objective under a limited review budget. An upstream pro…
The Moral Foundations Weibo Corpus
Renjie Cao, Miaoyan Hu, Jiahan Wei +1
Moral sentiments expressed in natural language significantly influence both online and offline environments, shaping behavioral styles and interaction patterns, including social me…