GEWU
中

Search articles

Type keywords to search published articles.

    Disciplines / Research questions

    Intelligence science

    10 research topics · 31 questions

    Catastrophic forgetting in continual learning and the plasticity–stability dilemma4 questions

    1. Applicability of Frobenius-Isometry Reinitialization (FIRE) under Restricted Past-Data Access and at Large-Language-Model Scale

    2. Completing the scaling-limit (DMFT) theory of continual learning: finite-width convergence, the learning-rate-driven lazy–rich transition, depth, and mitigation scaling

    3. Extending the readout-decomposition of activation change (RDAC) framework beyond one-hidden-layer linear, task-incremental continual learning

    4. Predictive theory of the architecture-level stability-plasticity trade-off in continual learning: when depth versus width favors stability or plasticity at matched parameter budgets

    Information cascade and group polarization in multi-agent collaboration2 questions

    1. Formalizing infostorms: the exact relations between information technologies and amplified pluralistic ignorance, informational cascades, and belief polarization, and design principles to prevent them

    2. Causal mechanism, generality, and ecological validity of polarization in collectives of autonomous generative-AI agents under echo chambers

    The trade-off between effective deletion and retained utility in machine unlearning3 questions

    1. A Principled Termination Criterion for the Machine-Unlearning Process

    2. Minimal alignment requirements and deletion guarantees for residual feature alignment unlearning of pre-trained models

    3. Representation geometry and unlearning fidelity: characterizing and closing the utility gap of label-free, representation-space approximate machine unlearning

    Performance reversal caused by over-optimization of reward models3 questions

    1. Cost-efficient and reliable reward-model evaluation via the degree of overoptimization

    2. Overoptimisation dynamics and stability of iterated RLHF beyond controlled small-scale settings

    3. Ground-Truth-Free Identification of Reward-Model Overoptimization Thresholds in Composite-Reward RLHF

    Out-of-distribution action value overestimation in offline reinforcement learning3 questions

    1. Safe out-of-distribution value generalization in offline reinforcement learning beyond the convex hull and its neighborhood

    2. Convergence and action-value gap guarantees for the Imagination-Limited Bellman operator under function approximation

    3. Finite-sample control of the segmentation error probability in uncertainty-penalized Q-learning with a consistency model (QDQ)

    Failures of compositional generalization in neuro-symbolic systems1 questions

    1. Closing the procedural composition gap on ClassicLogic: learning systems that compose known puzzle-solving strategies into novel multi-step plans

    Critical thresholds of error accumulation in long-horizon world-model rollouts4 questions

    1. Domain of validity of the phase-drift mechanism for autoregressive rollout error in latent-space reduced-order models of bluff-body wakes

    2. Empirical validity of the GEAF proxy for the joint node-edge error operator in Graph World Models beyond synthetic simulators

    3. Closing the residual cache-maintenance gap for open-ended autoregressive video diffusion, and extending drift mitigation to multi-shot generation

    4. Does the Coverage Account of World-Model Hallucination Transfer to Billion-Parameter Models and Real Robot Data?

    Inconsistency between chain-of-thought interpretability and true causal processes4 questions

    1. Ground-truth-validated chain-of-thought faithfulness measurement at both the step and CoT level

    2. Causal Origins of Implicit Post-Hoc Rationalization: Are Answer-Driving Biases Encoded Before Chain-of-Thought Generation?

    3. Generalizing and validating CoT-induced feature sparsity, interpretability, and causal transfer in language models beyond a single token position and small Pythia models

    4. Causal Origins and Generality of the Dissociation Between Chain-of-Thought Influence and Verbalised Faithfulness Across Post-Training Recipes

    Non-monotonic changes in agent tool-use ability with model scale3 questions

    1. Dynamic thinking policies and the generality of orchestration-over-scaling gains in small multi-agent LLM systems

    2. Why does inverse scaling become U-shaped? The causal mechanism and predictive boundaries of scaling-trend reversals in language models

    3. Execution-faithful evaluation of programmatic tool calling: certifying genuine tool execution beyond echo-return benchmarks

    Memory contamination versus true planning ability in agent benchmarks4 questions

    1. Contamination-resistant evaluation of LLM software-engineering agents: validated benchmark construction, temporal-freshness protocols, and black-box contamination detection

    2. Open problems in search-time contamination: comprehensive measurement, temporal dynamics, mitigation trade-offs, and evaluation-aware agent behavior

    3. Contamination detection for large reasoning models robust to RL-induced concealment and chain-of-thought contamination

    4. Belief-sufficient agent memory for interdependent multi-session tasks: representation, joint training, belief-fidelity evaluation, and the latency trade-off

    Back to open problems