Portrait de Sicheng Lyu n'est pas disponible

Sicheng Lyu

sicheng.lyu@mila.quebec
Maîtrise recherche - McGill
Superviseur⋅e principal⋅e
Doina Precup
Sujets de recherche
Grands modèles de langage (LLM)

Publications

Beyond Hard Writes and Rigid Preservation: Soft Recursive Least-Squares for Lifelong LLM Editing
Xinyu Wang
Sicheng Lyu
Yu Gu
Jerry Huang
Peng Lu
Yufei Cui
Xiao-Wen Chang
Model editing updates a pre-trained LLM with new facts or rules without retraining while preserving unrelated behavior. In real deployment, … (voir plus)edits arrive as long streams, creating a plasticity-stability dilemma: repeated locate-then-edit "hard writes" can accumulate interference over time, while rigid preservation constraints may protect only explicitly constrained directions, allowing past edits or unconstrained behaviors to deviate. We propose RLSEdit, a recursive least-squares editor for long sequential editing. RLSEdit formulates editing as an online quadratic optimization with soft constraints, minimizing a cumulative key-value fitting objective together with two regularizers that control deviation from the pre-trained weights and from a designated anchor mapping. This objective admits an efficient Woodbury-based online recursion, with per-edit cost independent of history length and scaling only with the current edit size. We further provide deviation bounds and an asymptotic characterization of the adherence-preservation trade-off in the many-edits regime. Experiments on CounterFact and ZsRE across multiple model families show stable scaling to 10K edits, outperforming strong baselines in both edit success and holistic stability, while retaining early edits and preserving general capabilities on GLUE and held-out reasoning/code benchmarks.
2026-08-31
International Joint Conference on Artificial Intelligence (publié)
doi.org
arxiv.org
FinSAgent: Corpus-Aligned Multi-Agent RAG Framework for Evidence-Grounded SEC Filing Question Answering
Jijun Chi
Zhenghan Tai
Hanwei Wu
Tung Sum Thomas Kwok
Hailin He
Zixing Liao
Bohuai Xiao
Chaolong Jiang
Jianliang Lei
Jerry Huang
Peng Lu
Muzhi Li
Liheng Ma
Yihong Wu
Sicheng Lyu
Jingrui Tian
Yihan Li
Yanzhang Ma
Sizhe Guan
Dingtao Hu … (voir 4 de plus)
Yufei Cui
Ling Zhou
Lei Ding
Xinyu Wang
Financial question answering over U.S. Securities and Exchange Commission (SEC) filings requires retrieving and synthesizing heterogeneous e… (voir plus)vidence dispersed across long, standardized, and highly redundant disclosures. Existing retrieval-augmented and multi-agent systems typically derive retrieval queries directly from the user's question and rank candidates by semantic similarity. Together, these choices create prior-corpus misalignment: a mismatch between model priors and the target filings' structure, terminology, and evidence standards. As a result, query generation misses corpus-specific evidence, while semantic reranking favors topically similar but evidentially invalid false-positive chunks. We propose FinSAgent, an evidence-grounded multi-agent framework that reframes SEC filing QA as corpus-aligned retrieval planning and corrects both ends with a single principle: inject corpus-side conditioning wherever model priors would otherwise dominate. FinSAgent combines (1) role-specialized agents anchored to the mandated 10-K item structure, (2) database-aware query decomposition that conditions each agent's sub-queries on a lightweight, summary-level view of the local corpus, and (3) multi-path retrieval with a learned feature-gated reranker that separates evidential validity from semantic similarity. Across five offline financial QA benchmarks, FinSAgent improves retrieval coverage and answer correctness over strong single-agent and multi-agent baselines; in a three-arm randomized online experiment with 1,000 anonymous user ratings, it also receives higher scores than baselines.
2026-07-19
arXiv (prépublication)
doi.org
arxiv.org
HoloQ-VLA: Uniform W4A4 Quantization of Vision-Language-Action Models
Xinyu Wang
Mingze Li
Sicheng Lyu
Dongxiu Liu
Kaicheng Yang
Ziyu Zhao
Yufei Cui
Xiao-Wen Chang
Peng Lu
Vision-Language-Action (VLA) models unify perception, reasoning, and control in a single policy, but their multi-billion-parameter backbones… (voir plus) and diffusion-based action heads make on-device deployment prohibitively expensive. Low-bit post-training quantization (PTQ) is the natural remedy, yet the diffusion action head that emits continuous control signals is highly sensitive to it: a few weight and activation outliers are enough to destabilize the head, so prior work leaves it at full precision or falls back to mixed-precision schemes, and uniformly quantizing the whole model to low bit-width remains an open challenge. We present HoloQ-VLA, the first training-free PTQ framework that compresses both the language backbone and the entire diffusion action head to uniform W4A4 precision without mixed-precision allocation. Instead of trading weight quality against activation quality, HoloQ-VLA targets the two outlier sources with complementary transforms: a weight-adapted rotation composed with an activation-dispersing Hadamard transform, together with per-step scaling that absorbs the dynamic-range drift exhibited by the action head across denoising steps. On LIBERO, HoloQ-VLA compresses Pi-0.5 and GR00T-N1.5 to W4A4 with 98.0% and 87.8% task success rates, matching or exceeding their FP16 references of 97.1% and 87.0%, while reducing the static memory footprint by 74.2%. Real-world manipulation experiments further demonstrate that HoloQ-VLA maintains smooth and accurate control across diverse real-world scenarios.
2026-05-26
arXiv (prépublication)
doi.org
arxiv.org
RL Fine-Tuning Heals OOD Forgetting in SFT
Hangzhan Jin
Sitao Luan
Sicheng Lyu
Guillaume Rabusseau
Reihaneh Rabbany
Doina Precup
Mohammad Hamdaqa
The two-stage fine-tuning paradigm of Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has empirically shown better reas… (voir plus)oning performance than one-stage SFT for the post-training of Large Language Models (LLMs). However, the evolution and mechanism behind the synergy of SFT and RL are still under-explored and inconclusive. In our study, we find the well-known claim "SFT memorizes, RL generalizes" is over-simplified, and discover that: (1) OOD performance peaks at the early stage of SFT and then declines (OOD forgetting), the best SFT checkpoint cannot be captured by training/test loss; (2) the subsequent RL stage does not generate fundamentally better OOD capability, instead it plays an \textbf{OOD restoration} role, recovering the lost reasoning ability during SFT; (3) The recovery ability has boundaries, \ie{} \textbf{if SFT trains for too short or too long, RL cannot recover the lost OOD ability;} (4) To uncover the underlying mechanisms behind the forgetting and restoration process, we employ SVD analysis on parameter matrices, manually edit them, and observe their impacts on model performance. Unlike the common belief that the shift of model capacity mainly results from the changes of singular values, we find that they are actually quite stable throughout fine-tuning. Instead, the OOD behavior strongly correlates with the \textbf{rotation of singular vectors}. Our findings re-identify the roles of SFT and RL in the two-stage fine-tuning and discover the rotation of singular vectors as the key mechanism. %reversing the rotations induced by SFT, which shows recovery from forgetting, whereas imposing the SFT parameter directions onto a RL-tuned model results in performance degradation. Code is available at https://github.com/xiaodanguoguo/RL_Heals_SFT
2025-09-07
arXiv (Cornell University) (prépublication)
doi.org
arxiv.org