BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Chao Li

Chao Li contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Artificial IntelligenceMachine LearningComputation and LanguageCryptography and Securityeess.SPeess.SYHardware ArchitectureInformation Retrievalmath.DGMultiagent SystemsSystems and Control

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
9works
0followers
11topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

9 published item(s)

preprint2026arXiv

Code Evolution for Control: Synthesizing Policies via LLM-Driven Evolutionary Search

Designing effective control policies for autonomous systems remains a fundamental challenge, traditionally addressed through reinforcement learning or manual engineering. While reinforcement learning has achieved remarkable success, it often suffers from high sample complexity, reward shaping difficulties, and produces opaque neural network policies that are hard to interpret or verify. Manual design, on the other hand, requires substantial domain expertise and struggles to scale across diverse tasks. In this work, we demonstrate that LLM-driven evolutionary search can effectively synthesize interpretable control policies in the form of executable code. By treating policy synthesis as a code evolution problem, we harness the LLM's prior knowledge of programming patterns and control heuristics while employing evolutionary search to explore the solution space systematically. We implement our approach using EvoToolkit, a framework that seamlessly integrates LLM-driven evolution with customizable fitness evaluation. Our method iteratively evolves populations of candidate policy programs, evaluating them against task-specific objectives and selecting superior individuals for reproduction. This process yields compact, human-readable control policies that can be directly inspected, modified, and formally verified. This work highlights the potential of combining foundation models with evolutionary computation for synthesizing trustworthy control policies in autonomous systems. Code is available at https://github.com/pgg3/EvoControl.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Dual LoRA: Enhancing LoRA with Magnitude and Direction Updates

Low-rank adaptation (LoRA) is one of the most popular methods among parameter-efficient fine-tuning (PEFT) methods to adapt pre-trained large language models (LLMs) to specific downstream tasks. However, the model trained based on LoRA often has an unsatisfactory performance due to its low-rank assumption. In this paper, we propose a novel method called Dual LoRA to improve the performance by incorporating an inductive bias into the original LoRA. Specifically, we separate low-rank matrices into two groups: the magnitude group to control whether or not and how far we should update a parameter and the direction group to decide whether this parameter should move forward or backward, to better simulate the parameter updating process of the full fine-tuning based on gradient-based optimization algorithms. We show that this can be simply achieved by adding a ReLU function to the magnitude group and a sign function to the direction group. We conduct several experiments over a wide range of NLP tasks, including natural language understanding (NLU) and commonsense reasoning datasets on RoBERTa, DeBERTa, and LLaMA-1/2/3 as baseline models. The results show that we consistently outperform LoRA and its state-of-the-art variants with the same number of trainable parameters.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

ICPO: Intrinsic Confidence-Driven Group Relative Preference Optimization for Efficient Reinforcement Learning

Reinforcement Learning with Verifiable Rewards (RLVR) demonstrates significant potential in enhancing the reasoning capabilities of Large Language Models (LLMs). However, existing RLVR methods are often constrained by issues such as coarse-grained rewards, reward noise, and inefficient exploration, which lead to unstable training and entropy collapse. To address this challenge, we propose the Intrinsic Confidence-Driven Group Relative Preference Optimization method (ICPO). The intuition behind it lies in the fact that the probabilities of an LLM generating different responses can inherently and directly reflect its self-assessment of the reasoning process. Inspired by the idea of preference modeling, ICPO calculates a preference advantage score for each response by comparing the relative generation probabilities of multiple responses under the same input prompt, and integrates this score with verifiable rewards to guide the exploration process. We have discovered that the preference advantage score not only alleviates the issues of coarse-grained rewards and reward noise but also effectively curbs overconfident errors, enhances the relative superiority of undervalued high-quality responses, and prevents the model from overfitting to specific strategies. Comprehensive experiments across four general-domain benchmarks and three mathematical benchmarks demonstrate that ICPO steadily boosts reasoning compared to GRPO.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Jailbreaking LLMs & VLMs: Mechanisms, Evaluation, and Unified Defense

This paper provides a systematic survey of jailbreak attacks and defenses on Large Language Models (LLMs) and Vision-Language Models (VLMs), emphasizing that jailbreak vulnerabilities stem from structural factors such as incomplete training data, linguistic ambiguity, and generative uncertainty. It further differentiates between hallucinations and jailbreaks in terms of intent and triggering mechanisms. We propose a three-dimensional survey framework: (1) Attack dimension-including template/encoding-based, in-context learning manipulation, reinforcement/adversarial learning, LLM-assisted and fine-tuned attacks, as well as prompt- and image-level perturbations and agent-based transfer in VLMs; (2) Defense dimension-encompassing prompt-level obfuscation, output evaluation, and model-level alignment or fine-tuning; and (3) Evaluation dimension-covering metrics such as Attack Success Rate (ASR), toxicity score, query/time cost, and multimodal Clean Accuracy and Attribute Success Rate. Compared with prior works, this survey spans the full spectrum from text-only to multimodal settings, consolidating shared mechanisms and proposing unified defense principles: variant-consistency and gradient-sensitivity detection at the perception layer, safety-aware decoding and output review at the generation layer, and adversarially augmented preference alignment at the parameter layer. Additionally, we summarize existing multimodal safety benchmarks and discuss future directions, including automated red teaming, cross-modal collaborative defense, and standardized evaluation.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Long-time behavior of the Hermitian-Yang-Mills flow on non-Kähler manifolds

In this paper, we study the long-time behavior of the Hermitian-Yang-Mills flow over compact Hermitian manifolds. We obtain the monotonicity of lower bound and upper bound of the eigenvalues of the mean curvature along the Hermitian-Yang-Mills flow. In the Gauduchon case, we show that the eigenvalues of the mean curvature converge to geometric invariants determined by the Harder-Narasimhan type. Furthermore, we generalize the Atiyah-Bott-Bando-Siu question to the non-Kähler case.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Modeling Descriptive Norms in Multi-Agent Systems: An Auto-Aggregation PDE Framework with Adaptive Perception Kernels

This paper presents a PDE-based auto-aggregation model for simulating descriptive norm dynamics in autonomous multi-agent systems, capturing convergence and violation through non-local perception kernels and external potential fields. Extending classical transport equations, the framework represents opinion popularity as a continuous distribution, enabling direct interactions without Bayesian guessing of beliefs. Applied to a real-world COVID-19 dataset from a major medical center, the experimental results demonstrate that: when clinical guidelines serve as a top-down constraint mechanism, it effectively generates convergence of novel descriptive norms consistent with the dataset; in the bottom-up experiment, potential field guidance successfully promotes the system's reconstruction of descriptive norms aligned with the dataset through violation-and-recoupling; whereas fully autonomous interaction leads to the emergence of multi-centric normative structures independent of the dataset.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Neural Operators for Biomedical Spherical Heterogeneity

Spherical deep learning has been widely applied to a broad range of real-world problems. Existing approaches often face challenges in balancing strong spherical geometric inductive biases with the need to model real-world heterogeneity. To solve this while retaining spherical geometry, we first introduce a designable Green's function framework (DGF) to provide new spherical operator solution strategy: Design systematic Green's functions under rotational group. Based on DGF, to model biomedical heterogeneity, we propose Green's-Function Spherical Neural Operator (GSNO) fusing 3 operator solutions: (1) Equivariant Solution derived from Equivariant Green's Function for symmetry-consistent modeling; (2) Invariant Solution derived from Invariant Green's Function to eliminate nuisance heterogeneity, e.g., consistent background field; (3) Anisotropic Solution derived from Anisotropic Green's Function to model anisotropic systems, especially fibers with preferred direction. Therefore, the resulting model, GSNO can adapt to real-world heterogeneous systems with nuisance variability and anisotropy while retaining spectral efficiency. Evaluations on spherical MNIST, Shallow Water Equation, diffusion MRI fiber prediction, cortical parcellation and molecule structure modeling demonstrate the superiority of GSNO.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

On the Approximation Complexity of Matrix Product Operator Born Machines

Matrix product operator Born machines (MPO-BMs) are tractable tensor-network models for probabilistic modeling, but their efficient approximation capability remains unclear. We characterize this boundary from both negative and positive perspectives. First, we prove that KL approximation is NP-hard for MPO-BMs in the continuous setting, ruling out universal efficient approximation in the worst case. Second, for score-based variational inference, we show that, under a locality and spectral-gap conditions on the loss-induced Hamiltonian, structured targets (e.g., path-graph Markov random fields) admit MPO-BM approximations with polynomial bond dimension and provable KL guarantees. Third, under the same locality structure, we prove that polynomially many score queries suffice to estimate the induced Hamiltonian and obtain such guarantees. Our results provide a theoretical characterization of when MPO-BMs are fundamentally hard to approximate and when they become efficiently learnable.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

PADE: A Predictor-Free Sparse Attention Accelerator via Unified Execution and Stage Fusion

Attention-based models have revolutionized AI, but the quadratic cost of self-attention incurs severe computational and memory overhead. Sparse attention methods alleviate this by skipping low-relevance token pairs. However, current approaches lack practicality due to the heavy expense of added sparsity predictor, which severely drops their hardware efficiency. This paper advances the state-of-the-art (SOTA) by proposing a bit-serial enable stage-fusion (BSF) mechanism, which eliminates the need for a separate predictor. However, it faces key challenges: 1) Inaccurate bit-sliced sparsity speculation leads to incorrect pruning; 2) Hardware under-utilization due to fine-grained and imbalanced bit-level workloads. 3) Tiling difficulty caused by the row-wise dependency in sparsity pruning criteria. We propose PADE, a predictor-free algorithm-hardware co-design for dynamic sparse attention acceleration. PADE features three key innovations: 1) Bit-wise uncertainty interval-enabled guard filtering (BUI-GF) strategy to accurately identify trivial tokens during each bit round; 2) Bidirectional sparsity-based out-of-order execution (BS-OOE) to improve hardware utilization; 3) Interleaving-based sparsity-tiled attention (ISTA) to reduce both I/O and computational complexity. These techniques, combined with custom accelerator designs, enable practical sparsity acceleration without relying on an added sparsity predictor. Extensive experiments on 22 benchmarks show that PADE achieves 7.43x speed up and 31.1x higher energy efficiency than Nvidia H100 GPU. Compared to SOTA accelerators, PADE achieves 5.1x, 4.3x and 3.4x energy saving than Sanger, DOTA and SOFA.

0 citations0 reviewsNo code linkedOpen access