From the 1 of 20 linked papers with an AI index.
19 papers
TrajWiki: Source-Grounded Memory Trajectories for Long-Horizon Dialogue Agents
Jingyu Sun, Yuyang Xue, Mingyang Li +9
Large language model agents have shown strong capabilities in generating coherent and contextually appropriate responses, yet robust long-horizon dialogue remains limited by the la…
PMMC: Prospective Multimodal Memory Compilation for Long-Term LVLM Agents
Jingyu Sun, Yan Lin, Yuyang Xue +10
Long-term memory is essential for LVLM agents to maintain consistency and integrate information across extended multimodal interactions. Existing agent memory systems, however, oft…
PreDiff-LM: Pretrained Discrete Masked Diffusion Language Modeling with Hybrid Attention
Zhengtao Yao, Runhao Li, Xupeng Chen +12
The paper presents PreDiff-LM, a discrete masked diffusion language model that retains causal attention on the prompt while applying bidirectional attention within masked targets,…
Less Data, Better Alignment: Data-Centric Multi-Evaluator Agreement for Preference Optimization
Zhengtao Yao, Runhao Li, Xupeng Chen +12
Research on preference optimization often varies the training objective while holding the data fixed. We instead ask whether a small, high-confidence set of on-policy responses can…
Seeing What Is Actually There: PriVE-Bench and PriVE-Tools for Counterfactual Evaluation of Agentic Visual Evidence in VLMs
Jingyu Sun, Jiachen Tu, Yuyang Xue +8
Vision-language models (VLMs) often answer visual questions using learned language and category priors rather than grounding their predictions in the image itself. Counterfactual i…
TimeROME-DLM: Temporal Causal Tracing and Low-Rank Inference-Time Knowledge Editing for Masked Diffusion Language Models
Zhengtao Yao, Liuyang Song, Hongbo Zhang +4
Masked diffusion language models (MDLMs) such as LLaDA now rival autoregressive (AR) LLMs, but every existing knowledge-editing and unlearning method (ROME, MEMIT, etc.) targets AR…