12 citations · 30 across the 12 of their papers we have counts for
15 papers
MemoProAgent: Toward Memory-Driven Proactive Assistance
Shenglai Zeng, Xiao Yang, Tiffany Ma +15
As assistants move from reactive answering toward proactive intervention, memory changes role: it no longer only supplies the answer to a query, it determines whether and when to s…
Graph Sensitivity of Cartesian Products with Matched Bridges
Zhen-Mu Hong, Zi-Yi Wu, Zheng-Jiang Xia
For a graph , let denote the minimum of the maximum degree of an induced subgraph with vertices, where is the independence number, and write $f(G)=f_1(G…
Sharpening Tax in Post-Training
Changdae Oh, Qi Zeng, Qi Qi +7
An emerging hypothesis about reinforcement learning (RL) post-training of large language models (LLMs) is that it merely sharpens existing behaviors of a base model, improving sing…
Agents' Last Exam
Yiyou Sun, Xinyang Han, Weichen Zhang +355
Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional d…
Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models
Hoang Phan, Xianjun Yang, Yuanshun Yao +6
Reinforcement learning with verifiable rewards (RLVR) has delivered impressive gains in mathematical and multimodal reasoning and has become a standard post-training paradigm for c…
FactCG: Enhancing Fact Checkers with Graph-Based Multi-Hop Data
Deren Lei, Yaxi Li, Siyao Li +6
Prior research on training grounded factuality classification models to detect hallucinations in large language models (LLMs) has relied on public natural language inference (NLI)…
InvisMark: Invisible and Robust Watermarking for AI-generated Image Provenance
Rui Xu, Mengya Hu, Deren Lei +6
The proliferation of AI-generated images has intensified the need for robust content authentication methods. We present InvisMark, a novel watermarking technique designed for high-…
SLM Meets LLM: Balancing Latency, Interpretability and Consistency in Hallucination Detection
Mengya Hu, Rui Xu, Deren Lei +5
Large language models (LLMs) are highly capable but face latency challenges in real-time applications, such as conducting online hallucination detection. To overcome this issue, we…
Chain of Natural Language Inference for Reducing Large Language Model Ungrounded Hallucinations
Deren Lei, Yaxi Li, Mengya Hu +4
Large language models (LLMs) can generate fluent natural language texts when given relevant documents as background context. This ability has attracted considerable interest in dev…
Extract, Denoise and Enforce: Evaluating and Improving Concept Preservation for Text-to-Text Generation
Yuning Mao, Wenchang Ma, Deren Lei +2
Prior studies on text-to-text generation typically assume that the model could figure out what to attend to in the input and what to include in the output via seq2seq learning, wit…
Learning to Reason in Round-based Games: Multi-task Sequence Generation for Purchasing Decision Making in First-person Shooters
Yilei Zeng, Deren Lei, Beichen Li +3
Sequential reasoning is a complex human ability, with extensive previous research focusing on gaming AI in a single continuous game, round-based decision makings extending to a seq…
Learning Collaborative Agents with Rule Guidance for Knowledge Graph Reasoning
Deren Lei, Gangrong Jiang, Xiaotao Gu +3
Walk-based models have shown their advantages in knowledge graph (KG) reasoning by achieving decent performance while providing interpretable decisions. However, the sparse reward…
Deep Reinforcement Learning with Distributional Semantic Rewards for Abstractive Summarization
Siyao Li, Deren Lei, Pengda Qin +1
Deep reinforcement learning (RL) has been a commonly-used strategy for the abstractive summarization task to address both the exposure bias and non-differentiable task issues. Howe…
Imposing Label-Relational Inductive Bias for Extremely Fine-Grained Entity Typing
Wenhan Xiong, Jiawei Wu, Deren Lei +4
Existing entity typing systems usually exploit the type hierarchy provided by knowledge base (KB) schema to model label correlations and thus improve the overall performance. Such…
Implicit Regularization of Stochastic Gradient Descent in Natural Language Processing: Observations and Implications
Deren Lei, Zichen Sun, Yijun Xiao +1
Deep neural networks with remarkably strong generalization performances are usually over-parameterized. Despite explicit regularization strategies are used for practitioners to avo…