2 citations · 4 across the 17 of their papers we have counts for
21 papers
Harmful Responses Are Jailbreak Templates: Transferring Autoregressive Jailbreaks to Diffusion Language Models
Jinwei Gan, Zifeng Cheng, Zhiwei Jiang +3
Diffusion large language models (dLLMs) enable flexible masked generation through bidirectional context modeling, but this capability also introduces a distinct jailbreak attack su…
Selecting What Matters: Semantic Compression-Guided Selective Pooling for Long-Context Embeddings
Zifeng Cheng, Jie Zheng, Zhiwei Jiang +4
Large language models (LLMs) have shown strong potential as training-free text encoders for long-context embeddings. Existing approaches primarily improve information flow under ca…
Focusing Condition: Inference-Time Self-Contrastive Steering Elicits Better Conditional Text Embeddings in LLMs
Zifeng Cheng, Lingyun Qian, Zhiwei Jiang +5
Extracting conditional text embeddings from large language models (LLMs) is a promising paradigm, as it requires neither additional data nor fine-tuning. Existing methods incorpora…
Accelerating Diffusion Language Models via Structured Suffix Modeling
Zifeng Cheng, Keda Li, Zhiwei Jiang +3
Diffusion Language Models (DLMs) exhibit strong parallel decoding capabilities by denoising multiple tokens in a single generation step. However, this parallelism comes with substa…
Dynamic Distribution-Aware Uncertainty Tracking in Vision-Language Representation Learning
Ao Zhou, Zhiwei Jiang, Zifeng Cheng +4
Uncertainty Quantification (UQ) aims to measure the reliability of model predictions, serving as a critical safeguard for deploying Vision-Language Models (VLMs) in safety-critical…
Step-Level On-Policy Distillation: Interpolating Between On-Policy Distillation and Supervised Fine-Tuning
Changhui Sun, Lanbo Liu, Hang Lei +11
On-policy distillation (OPD) aligns a student model with a teacher's logit distribution on student-generated trajectories. This approach has achieved strong empirical gains and can…
ScaleErasure: Inference-Time Minimal Intervention for Precise Concept Erasure in Next-Scale Autoregressive Image Generation
Cong Wang, Haiyu Wu, Zhiwei Jiang +4
Concept erasure aims to prevent image generative models from producing unsafe content while preserving their general generative capability. Meanwhile, next-scale autoregressive (AR…
Multi-Label Test-Time Adaptation with Bayesian Conditional Priors
Qiru Li, Ao Zhou, Zhiwei Jiang +4
Multi-label recognition with frozen Vision-Language Models (VLMs) is brittle under distribution shift: standard zero-shot inference scores labels independently, ignoring co-occurre…
RegionMarker: A Region-Triggered Semantic Watermarking Framework for Embedding-as-a-Service Copyright Protection
Shufan Yang, Zifeng Cheng, Zhiwei Jiang +5
Embedding-as-a-Service (EaaS) is an effective and convenient deployment solution for addressing various NLP tasks. Nevertheless, recent research has shown that EaaS is vulnerable t…
Steering When Necessary: Flexible Steering Large Language Models with Backtracking
Zifeng Cheng, Jinwei Gan, Zhiwei Jiang +5
Large language models (LLMs) have achieved remarkable performance across many generation tasks. Nevertheless, effectively aligning them with desired behaviors remains a significant…
Hierarchical Vision-Language Reasoning for Multimodal Multiple-Choice Question Answering
Ao Zhou, Zebo Gu, Tenghao Sun +6
Multimodal Large Language Models (MLLMs) have demonstrated remarkable multimodal understanding capabilities in Visual Question Answering (VQA) tasks by integrating visual and textu…
Cross-Modal Prototype Augmentation and Dual-Grained Prompt Learning for Social Media Popularity Prediction
Ao Zhou, Mingsheng Tu, Luping Wang +5
Social Media Popularity Prediction is a complex multimodal task that requires effective integration of images, text, and structured information. However, current approaches suffer…
Advanced Sign Language Video Generation with Compressed and Quantized Multi-Condition Tokenization
Cong Wang, Zexuan Deng, Zhiwei Jiang +6
Sign Language Video Generation (SLVG) seeks to generate identity-preserving sign language videos from spoken language texts. Existing methods primarily rely on the single coarse co…
Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering
Zifeng Cheng, Zhonghui Wang, Yuchen Fu +4
Extracting sentence embeddings from large language models (LLMs) is a practical direction, as it requires neither additional data nor fine-tuning. Previous studies usually focus on…
Implicit Location-Caption Alignment via Complementary Masking for Weakly-Supervised Dense Video Captioning
Shiping Ge, Qiang Chen, Zhiwei Jiang +4
Weakly-Supervised Dense Video Captioning (WSDVC) aims to localize and describe all events of interest in a video without requiring annotations of event boundaries. This setting pos…
Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs
Yuchen Fu, Zifeng Cheng, Zhiwei Jiang +4
Extracting sentence embeddings from large language models (LLMs) is a promising direction, as LLMs have demonstrated stronger semantic understanding capabilities. Previous studies…
A Debiased Nearest Neighbors Framework for Multi-Label Text Classification
Zifeng Cheng, Zhiwei Jiang, Yafeng Yin +5
Multi-Label Text Classification (MLTC) is a practical yet challenging task that involves assigning multiple non-exclusive labels to each document. Previous studies primarily focus…
Multi-Prompting Decoder Helps Better Language Understanding
Zifeng Cheng, Zhaoling Chen, Zhiwei Jiang +4
Recent Pre-trained Language Models (PLMs) usually only provide users with the inference APIs, namely the emerging Model-as-a-Service (MaaS) setting. To adapt MaaS PLMs to downstrea…
Unifying Token and Span Level Supervisions for Few-Shot Sequence Labeling
Zifeng Cheng, Qingyu Zhou, Zhiwei Jiang +3
Few-shot sequence labeling aims to identify novel classes based on only a few labeled samples. Existing methods solve the data scarcity problem mainly by designing token-level or s…
Controlling Class Layout for Deep Ordinal Classification via Constrained Proxies Learning
Cong Wang, Zhiwei Jiang, Yafeng Yin +3
For deep ordinal classification, learning a well-structured feature space specific to ordinal classification is helpful to properly capture the ordinal nature among classes. Intuit…
Learning to Classify Open Intent via Soft Labeling and Manifold Mixup
Zifeng Cheng, Zhiwei Jiang, Yafeng Yin +2
Open intent classification is a practical yet challenging task in dialogue systems. Its objective is to accurately classify samples of known intents while at the same time detectin…