Bo Wang
Publications
Seen, Said, or Forgotten? A Causal Audit of Visual KV Memory Across Dialog Turns
Stateful multimodal assistants encode an image once but may answer questions about it many turns later. Attention-guided visual-KV eviction assumes that evidence irrelevant now will remain dispensable, although future questions are unknown. We ask when a visual fact is actually safe to forget and introduce the Causal Visual Memory Audit (CVMA), a paired single-prefill framework that tests what later answers lose when a visual region, the whole image, or prior assistant text becomes unavailable. On VisDial and ConvBench, current attention can rank future-useful regions worse than random even though a diagnostic marginal-utility control shows substantial selection headroom. Aggregate scores hide this failure when later turns do not need vision; controlled and stock-generated histories reveal a second escape route, in which assistant-text KV replaces image KV for facts already stated but not reliably for unstated facts. In the tested stacks, safe forgetting is supported by low future visual dependence or fact-specific verbalization---not by low current attention.
OrpQuant: Geometric Orthogonal Residual Projection for Multiplier-Free Power-of-Two Transformer Quantization
The deployment of Large Language Models (LLMs) and Vision Transformers (ViTs) on edge devices is significantly constrained by memory limitations and the critical timing bottlenecks introduced by dense Multiply-Accumulate (MAC) arrays. In the ultra-low bit regime, logarithmic Power-of-Two (PoT) quantization provides a hardware-efficient alternative by replacing MAC operations with bit-shifts. However, the non-uniform exponential lattice is inherently limited by a \textbf{Low Angular Resolution Regime}, a structural flaw that becomes particularly pronounced at sub-4-bit thresholds, leading to a notable degradation of high-dimensional feature manifolds. To address this geometric limitation, we propose Orthogonal Residual Projection (ORP), an algorithm-hardware co-design framework. By formulating quantization as a dual-basis geometric projection, ORP adaptively synthesizes a higher-resolution residual lattice using strictly shift-and-add operations. Furthermore, ORP's analytical solver offers a practical alternative to computationally intensive gradient-based optimization, reducing the full-model calibration time for LLaMA-2-7B to approximately \textbf{15 minutes}. Extensive evaluations demonstrate ORP's applicability across modalities and its hardware efficiency. Under the 3-bit (W3/A16) constraint, ORP achieves a perplexity of 6.10 on LLaMA-2-7B, comparing favorably to conventional MAC-intensive baselines like AWQ without relying on asymmetric scaling, while maintaining competitive accuracy in 4-bit scenarios. At the silicon level, standard-cell RTL synthesis at a 28nm node indicates that ORP effectively mitigates the timing bottlenecks associated with dense multiplier trees.
Deconstructing Pre-training: Knowledge Attribution Analysis in MoE and Dense Models
Mixture-of-Experts (MoE) architectures decouple model capacity from per-token computation, enabling scaling beyond the computational limits imposed by dense scaling laws. Yet how MoE architectures shape knowledge acquisition during pre-training, and how this process differs from dense architectures, remains unknown. To address this issue, we introduce Gated-LPI (Log-Probability Increase), a neuron-level attribution metric that decomposes log-probability increase across neurons. We present a time-resolved comparison of knowledge acquisition dynamics in MoE and dense architectures, tracking checkpoints over 1.2M training steps (~ 5.0T tokens) and 600K training steps (~ 2.5T tokens), respectively. Our experiments uncover three patterns: (1) Low-entropy backbone. The top approximately 1% of MoE neurons capture over 45% of positive updates, forming a high-utility core, which is absent in the dense baseline. (2) Early consolidation. The MoE model locks into a stable importance profile within < 100K steps, whereas the dense model remains volatile throughout training. (3) Functional robustness. Masking the ten most important MoE attention heads reduces relational HIT@10 by < 10%, compared with > 50% for the dense model, showing that sparsity fosters distributed -- rather than brittle -- knowledge storage. These patterns collectively demonstrate that sparsity fosters an intrinsically stable and distributed computational backbone from early in training, helping bridge the gap between sparse architectures and training-time interpretability.