We have 13 of 61 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Self-improving LLM agents increasingly distill successful experiences into persistent, reusable skills. Existing skill attack methods corrupt this learning pipeline by injecting malicious triggers, behaviors, or false facts into individual experiences or extracted skills. However, such attacks are easily detected, and...
Long-term memory enables LLM-based agents to retain and reuse information across tasks and sessions, supporting personalization and long-horizon interactions. However, persistent memories can also induce sycophancy, causing agents to over-align with users'historical beliefs even when they are inaccurate, outdated, or i...
Genomic prediction can accelerate crop breeding by predicting phenotypes from genome-wide SNP sequences. In practice, this task operates in a severe p \gg n regime, hundreds of thousands to millions of SNPs but only thousands of samples, making end-to-end deep learning prone to overfitting. Genomic foundation models he...
LA-CPD is proposed, a structured method that transforms noisy sentence-level score sequences into coherent authorship segments and outperforms WCP+AIC, increasing sentence-level accuracy from 0.747 to 0.796 while improving boundary localization and LLM-span delineation.
Large Language Models (LLMs) increasingly participate in writing by modifying or extending human drafts, causing machine involvement to vary in both form and extent. Yet most Machine-Generated Text (MGT) detectors are evaluated only on fully human-written versus fully AI-generated text. Because human--AI collaboration...
This paper examines Data Agents from a harness-centric perspective, introducing a taxonomy of Data Agents and associated data environments, and identifying four open reliability problems: inactive semantic calibration, missing clarification, missing experience transfer, and the missing verification-repair repository.
The Trajectory-guided Forget-Recover Network (TFR-Net) is proposed, which separates persistent target-related channels from transient hotspots and suppresses only the persistent ones, and achieves a more favorable trade-off between unlearning effectiveness and retained utility than representative baselines.
HVM-GraphRAG uses a holistic view to guide graph construction, thereby reducing noisy and conflicting graph updates and building reliable indices between concept-level graph nodes and supporting multimodal chunks and enabling the answering model to better integrate heterogeneous evidence.
Graph Engineering is introduced, an emerging paradigm for next-generation agent systems that provides a unified foundation for organizing complex objectives, orchestrating heterogeneous agents, modeling system dynamics, and enabling scalable agent evolution.
CrossModalQA is introduced, an open-domain benchmark for evaluating multimodal retrieval and reasoning over heterogeneous corpora and it is revealed that complete cross-modal retrieval contributes more to answer accuracy than generator scaling, while multi-image retrieval and reasoning remain the primary bottlenecks li...
CulturalMenuBench shows that near-perfect recognition can conceal an inability to apply cultural knowledge, motivating training that explicitly connects perception, procedure, and cultural context.
The results show that structured agent memory need not generate an intermediate representation of the past, and Zero-Mem achieves competitive performance while eliminating LLM calls and LLM-token consumption from memory operations.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
