arXiv subjects

Rongrong Zhang

Publications and source records attributed to Rongrong Zhang.

7 recordsLinked to original sources

arXiv2026

Granularity-Adaptive Credit Assignment for Long-Horizon LLM Agent Reinforcement Learning

Reinforcement learning is now the standard way to train large language model agents on long-horizon tasks, where dozens of interdependent actions precede a single sparse reward. Critic-free, group-relative methods such as GRPO suit this regime, but they broadcast one trajectory-level scalar to every step and cannot say which decision drove the outcome. GiGPO recovers a step-level signal by grouping time steps that share an anchor state, yet it merges the step- and episode-level estimates under one fixed weight, spending the same resolution on a pivotal branching decision as on a routine, near-deterministic transition. We argue that the right resolution is state-dependent, and propose GACA, a critic-free estimator whose granularity follows an uncertainty-based criticality proxy. GACA scores every step by the negative log-likelihood its own rollout already records, then blends the two advantages with a per-step weight that grows with that score, so the gradient places more weight on the fine-grained signal at above-average NLL and on the episode-level signal below it. We derive an exact risk decomposition for the implemented mixture and show that sufficiently small modulation improves on fixed mixing under positive directional alignment. A separate conditional result bounds local action-value variation using expected NLL, while an error-projection analysis characterizes when mixing adds value beyond scalar uncertainty reweighting. On ALFWorld and WebShop, GACA improves task success over GRPO and GiGPO at both 1.5B and 7B scales.

cs.LG↗

arXiv2026

On Existence Theorems for Conditional Inferential Models

The framework of Inferential Models (IMs) has recently been developed in search of what is referred to as the holy grail of statistical theory, that is, prior-free probabilistic inference. Its method of Conditional IMs (CIMs) is a critical component in that it serves as a desirable extension of the Bayes theorem for combining information when no prior distribution is available. The general form of CIMs is defined by a system of first-order homogeneous linear partial differential equations (PDEs). When admitting simple solutions, they are referred to as regular, whereas when no regular CIMs exist, they are used as the so-called local CIMs. This paper provides conditions for regular CIMs, which are shown to be equivalent to the existence of a group-theoretical representation of the underlying statistical model. It also establishes existence theorems for CIMs, which state that under mild conditions, local CIMs always exist. Finally, the paper concludes with a simple example and a few remarks on future developments of CIMs for applications to popular but inferentially nontrivial statistical models.

math.ST↗

arXiv2026

RigPI: Dynamic Parameter Identification of Rigid Body via VLM-Seeded Differentiable Simulation

Accurate physical parameter identification of manipulated objects is fundamental to advanced robotic manipulation and the construction of faithful digital twins. However, acquiring physically consistent inertial and frictional properties from real-world interactions remains challenging due to sensing noise, modeling errors, and limited prior knowledge. This paper presents RigPI, a systematic framework for identifying dynamic parameters of both unconstrained rigid bodies and multi-link rigid bodies during robot-object interaction. RigPI integrates vision-based semantic priors, force-torque measurements, and motion observations within a differentiable simulation pipeline. A vision-language model (VLM) provides informed initialization and a constrained search space, while gradient information from a differentiable physics simulator enables efficient and stable parameter refinement. The proposed two-stage optimization strategy alleviates sensitivity to noise and avoids physically implausible solutions. Extensive real-world experiments on objects with revolute and prismatic joints demonstrate that RigPI achieves accurate and stable parameter estimates, and successfully reproduces manipulation trajectories on a real robot with parameter-aware predictive validity. These results highlight the effectiveness and robustness of RigPI for real-world robotic system identification tasks.

cs.RO↗

arXiv2026

MISID: A Multimodal Multi-turn Dataset for Complex Intent Recognition in Strategic Deception Games

Understanding human intent in complex multi-turn interactions remains a fundamental challenge in human-computer interaction and behavioral analysis. While existing intent recognition datasets focus mainly on single utterances or simple dialogues, real-world scenarios often involve sophisticated strategic interactions where participants must maintain complex deceptive narratives over extended periods. To address this gap, we introduce MISID, a comprehensive multimodal, multi-turn, and multi-participant benchmark for intent recognition. Sourced from high-stakes social strategy games, MISID features a fine-grained, two-tier multi-dimensional annotation scheme tailored for long-context discourse analysis and evidence-based causal tracking. Our systematic evaluation of state-of-the-art Multimodal Large Language Models (MLLMs) on MISID reveals critical deficiencies in complex scenarios, including text-prior visual hallucination, impaired cross-modal synergy, and limited capacity in chaining causal cues. Consequently, we propose FRACTAM as a baseline framework. Using a ``Decouple-Anchor-Reason'' paradigm, FRACTAM reduces text bias by extracting pure unimodal factual representations, employs two-stage retrieval for long-range factual anchoring, and constructs explicit cross-modal evidence chains. Extensive experiments demonstrate that FRACTAM enhances mainstream models' performance in complex strategic tasks, improving hidden intent detection and inference while maintaining robust perceptual accuracy. Our dataset is available at https://naislab.cn/datasets/MISID.

cs.AI↗

arXiv2024

Synthetic frequency-controlled gene circuits unlock expanded cellular states

Natural biological systems process environmental information through both amplitude and frequency-modulated signals, yet engineered biological circuits have largely relied on amplitude-based regulation alone. Despite the prevalence of frequency-encoded signals in natural systems, fundamental challenges in designing and implementing frequency-responsive gene circuits have limited their development in synthetic biology. Here we present a Time-Resolved Gene Circuit (TRGC) architecture that enables frequency-to-amplitude signal conversion in engineered biological systems. Through systematic analysis, we establish a theoretical framework that guides the design of synthetic circuits capable of distinct frequency-dependent responses, implementing both high-pass and low-pass filtering behaviors. To enable rigorous characterization of these dynamic circuits, we developed a high-throughput automated platform that ensures stable and reproducible measurements of frequency-dependent r esponses across diverse conditions. Using this platform, we demonstrate that these frequency-modulated circuits can access cellular states unreachable through conventional amplitude modulation, significantly expanding the controllable gene expression space in multi-gene systems. Our results show that frequency modulation expands the range of achievable expression patterns when controlling multiple genes through a single input, demonstrating a new paradigm for engineering cellular behaviors. This work establishes frequency modulation as a powerful strategy for expanding the capabilities of engineered biological systems and enhancing cellular response to dynamic signals.

physics.bio-ph↗

arXiv2024

Optimal Frequency in Second Messenger Signaling Quantifying cAMP Information Transmission in Bacteria

Bacterial second messengers are crucial for transmitting environmental information to cellular responses. However, quantifying their information transmission capacity remains challenging. Here, we engineer an isolated cAMP signaling channel in Pseudomonas aeruginosa using targeted gene knockouts, optogenetics, and a fluorescent cAMP probe. This design allows precise optical control and real-time monitoring of cAMP dynamics. By integrating experimental data with information theory, we reveal an optimal frequency for light-mediated cAMP signaling that maximizes information transmission, reaching about 40 bits/h. This rate correlates strongly with cAMP degradation kinetics and employs a two-state encoding scheme. Our findings suggest a mechanism for fine-tuned regulation of multiple genes through temporal encoding of second messenger signals, providing new insights into bacterial adaptation strategies. This approach offers a framework for quantifying information processing in cellular signaling systems.

physics.bio-ph↗

arXiv2017

Using Deep Neural Networks to Automate Large Scale Statistical Analysis for Big Data Applications

Statistical analysis (SA) is a complex process to deduce population properties from analysis of data. It usually takes a well-trained analyst to successfully perform SA, and it becomes extremely challenging to apply SA to big data applications. We propose to use deep neural networks to automate the SA process. In particular, we propose to construct convolutional neural networks (CNNs) to perform automatic model selection and parameter estimation, two most important SA tasks. We refer to the resulting CNNs as the neural model selector and the neural model estimator, respectively, which can be properly trained using labeled data systematically generated from candidate models. Simulation study shows that both the selector and estimator demonstrate excellent performances. The idea and proposed framework can be further extended to automate the entire SA process and have the potential to revolutionize how SA is performed in big data analytics.

stat.ML↗