6 papers
REWIND: Uncertainty-Guided Trajectory Repair for Test-Time Reasoning
Yi Ding, Mengyu Wang, Min Zhou +1
An early mistake in the generated reasoning can constrain all subsequent reasoning. Repeated-generation methods, like MCMC-based approaches, attempt to improve output quality by sa…
Learning to Look Again: Loss-Gap Supervision for Free-form Crop Routing in Vision-Language Models
Jinchang Zhu, Rong Fu, Yi Ding +3
Vision-language models (VLMs) fail many detail-centric questions for a concrete reason: the answer is visible in the image, yet lost after the image is compressed into a low-resolu…
SCIT: Testing Causal Cache Carriers in Latent Chain-of-Thought Models
Yi Ding, Lijun Huang, Menglin Yang
Latent chain-of-thought models move intermediate reasoning from emitted text into continuous states, improving compactness but hiding the causal object. We introduce SCIT, the Suff…
Learning When Not to Listen: Selective Anti-Interference Pretraining for Language Models
Jinchang Zhu, Haowei He, Yi Ding +5
Language models can over-condition on irrelevant preceding text: predictions already supported by local context may still change when distant, unrelated prefix tokens are perturbed…
FCPRAG: Fusion-Controller Parametric Retrieval-Augmented Generation for Stable Multi-Passage LoRA Injection
Jinchang Zhu, Jindong Li, Yi Ding +5
Parametric retrieval-augmented generation (PRAG) injects retrieved evidence into a large language model (LLM) through passage-specific LoRA adapters, reducing reliance on long in-c…
PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference
Niqi Lyu, Pengtao Shi, Wei Qiu +4
Large language models (LLMs) provide strong reasoning capabilities but are expensive to serve at scale, whereas small language models (SLMs) are cheaper but less reliable on diffic…