Papers by Wenhao Teng

4 papers
Harmonizing the Past, Present, and Future: A Null-Space Constrained Region-Specific Method for Continual Learning in LLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing continual learning paradigms prioritize instant performance through dense updates, leading to catastrophic forgetting and rapid exhaustion of model capacity.
Approach: They propose a method that preserves previously acquired knowledge and acquires new task-specific skills while preserving sufficient parameter capacity for subsequent adaptation.
Outcome: The proposed method is based on the brain's functional partitioning and can be used to map tasks between specialized and generalist neurons.
Learning How to Remember: A Meta-Cognitive Management Method for Structured and Transferable Agent Memory (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches store memory in fixed representations and reuse it at a single or implicit level of abstraction, which limits generalization and often leads to negative transfer when distribution shift.
Approach: They propose a Meta-Cognitive Memory Abstraction method which decouples task execution from memory management by combining a frozen task model with a learned memory copilot.
Outcome: Experiments on ALFWorld, ScienceWorld, and BabyAI show that the proposed method improves performance, out-of-distribution generalization, and cross-task transfer over several baselines.
LANTERN in the Event Stream: Training-Free Temporal Knowledge Graph Forecasting by Balancing Inertia and Shifts (2026.findings-acl)

Copied to clipboard

Challenge: Temporal knowledge graph forecasting (TKGF) uses long-window strengthscores and short-windowed novelty scores to predict missing entities in future queries.
Approach: They propose a training-freeprompting framework that uses two perspectives of history to predict missing entities in future queries.
Outcome: The proposed framework outperforms the state-of-the-art baselineAnRe framework in ICEWS14, ICEW05-15, and GDELT.
Spectral Disentanglement: Rank-Aware Task Adaptation for Rehearsal-free Continual Learning in LLMs (2026.acl-long)

Copied to clipboard

Challenge: Continual Learning (CL) for Large Language Models faces a fundamental Stability-Plasticity Dilemma . Rank-Blindness enforces a single rank constraint across diverse tasks, leading to catastrophic forgetting of earlier tasks and underfitting on complex new ones.
Approach: They propose a rank-spectrum-based rehearsal-free framework that explicitly disentangles knowledge into two orthogonal subspaces.
Outcome: The proposed framework achieves a superior stability-plasticity balance compared to single-rank baselines.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations