7 papers
Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models
Ziwei Luo, Ziqi Jin, Lei Wang +2
This work presents self-rewarding sequential Monte Carlo (SMC), an inference-time scaling algorithm enabling effective sampling of masked diffusion language models (MDLMs). Our alg…
DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation
Yibo Wang, Lei Wang, Yue Deng +7
Deep research systems are widely used for multi-step web research, analysis, and cross-source synthesis, yet their evaluation remains challenging. Existing benchmarks often require…
UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning
Tiancheng Gu, Kaicheng Yang, Kaichen Zhang +6
Universal multimodal embedding models are foundational to various tasks. Existing approaches typically employ in-batch negative mining by measuring the similarity of query-candidat…
FedReFT: Federated Representation Fine-Tuning with All-But-Me Aggregation
Fatema Siddika, Md Anwar Hossen, J. Pablo Muñoz +3
Parameter-efficient fine-tuning (PEFT) adapts large pre-trained models by updating only a small subset of parameters. Recently, Representation Fine-Tuning (ReFT) has emerged as an…
Evolving Prompts In-Context: An Open-ended, Self-replicating Perspective
Jianyu Wang, Zhiqiang Hu, Lidong Bing
We propose a novel prompt design paradigm that challenges conventional wisdom in large language model (LLM) prompting. While conventional wisdom prioritizes well-crafted instructio…
MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Search
Zonglin Yang, Wanhao Liu, Ben Gao +7
Large language models (LLMs) have shown promise in automating scientific hypothesis generation, yet existing approaches primarily yield coarse-grained hypotheses lacking critical m…