arXiv subjects

Tianren Zhang

Publications and source records attributed to Tianren Zhang.

16 recordsLinked to original sources

arXiv2026

Molecular representation shapes the balance between target fidelity and exploration in flow based polymer generation

Designing polymers with targeted properties requires navigating vast chemical spaces from limited labeled data. Here we introduce PolyLatentFlow, a framework based on continuous-time flow matching in latent space for unconditional and conditional polymer generation, together with LlamaUni, a multimodal representation combining polymer sequence and 3D structural information. In unconditional generation, PolyLatentFlow with LlamaUni produced the largest yield of valid candidates novel relative to PolyInfo among the evaluated unconditional generators while maintaining high diversity. For $T_g$ conditioning, generated property distributions shifted systematically across a 200 °C target range. In multi-property tasks, molecular representations showed similar surrogate target fidelity but differed markedly in validity, training-set replay, and structural proximity to labeled polymers. PolyLatentFlow with LlamaUni consistently combined high validity with low replay and achieved the largest per-attempt yield of nonreplayed target hits for CO$_2$/N$_2$ conditioning. These results demonstrate latent space flow matching for polymer inverse design and identify molecular representation as a key determinant of target control and exploration beyond labeled chemistry.

physics.chem-ph↗

arXiv2026

Quantifying and Optimizing Simplicity via Polynomial Representations

Deep networks often exhibit a preference for "simple" solutions, and such a simplicity bias is widely believed to play a key role in generalization. Yet a broadly applicable, quantitative measure of simplicity remains elusive. We introduce polynomial representations as a distribution-aware, low-dimensional surrogate for neural functions: we approximate a network's predictive behavior along data-dependent interpolation paths using orthogonal polynomial bases, yielding a compact functional representation. We show that the effective degree of this representation serves as a practical simplicity metric that is predictive of generalization across tasks and architectures, and consistently outperforms existing generalization proxies such as sharpness. Finally, polynomial representations naturally yield a differentiable simplicity regularizer, which consistently improves generalization in image and text classification, fine-tuning contrastive vision-language models, and reinforcement learning.

cs.AI↗

arXiv2026

Semantic-Enriched Latent Visual Reasoning

Multimodal latent-space reasoning aims to replace explicit thinking with images by performing visual reasoning directly in a compact latent space. However, existing approaches largely rely on visual supervision and produce latent representations that lack sufficient semantic richness, limiting their ability to support diverse region-level reasoning tasks. In this work, we introduce Semantic-Enriched Latent Visual Reasoning (SLVR), a two-stage learning framework that enriches latent representations with attribute-level visual semantics and aligns them with diverse reasoning objectives. In the first stage, SLVR learns semantically enriched region-centric latents under fine-grained attribute supervision. In the second stage, we design Multi-query Group Relative Policy Optimization (M-GRPO) to align latent representations across multiple queries grounded in the same region. To support this framework, we construct SLV-Set, comprising approximately 400K region-level attribute annotations and 800K multi-query question answering samples, and introduce SV-QA, a benchmark that evaluates latent reasoning under semantic variation. Experiments demonstrate that SLVR improves the robustness and semantic consistency of latent visual reasoning compared to existing baselines.

cs.CV↗

arXiv2026

DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful Reasoning

Recent advances in multimodal language models (MLLMs) have made thinking with images a dominant paradigm for multimodal reasoning. However, existing methods still fail to ensure evidence-answer consistency, where correct answers must be supported by correct visual evidence. To address this issue, we propose DeFacto, a counterfactual reasoning framework that explicitly aligns visual evidence with final answers. Our approach integrates three complementary training paradigms: positive, counterfactual, and random-masking. We further develop a language-guided evidence construction pipeline that automatically localizes question-relevant regions and generates counterfactual variants, resulting in DeFacto-100K. Building on this dataset, we train MLLMs with GRPO-based reinforcement learning and design three complementary rewards to promote correct answering, structured reasoning, and consistent evidence selection. Moreover, we introduce DeFacto-1.5K, a human-annotated benchmark for systematically evaluating evidence-grounded consistency beyond answer accuracy. Experiments on diverse benchmarks demonstrate that DeFacto substantially improves both answer accuracy and evidence-answer consistency over strong baselines.

cs.AI↗

arXiv2026

Reconciling In-Context and In-Weight Learning via Dual Representation Space Encoding

In-context learning (ICL) is a valuable capability exhibited by Transformers pretrained on diverse sequence tasks. However, previous studies have observed that ICL often conflicts with the model's inherent in-weight learning (IWL) ability. By examining the representation space learned by a toy model in synthetic experiments, we identify the shared encoding space for context and samples in Transformers as a potential source of this conflict. To address this, we modify the model architecture to separately encode the context and samples into two distinct spaces: a task representation space and a sample representation space. We model these two spaces under a simple yet principled framework, assuming a linear representational structure and treating them as a pair of dual spaces. Both theoretical analysis and empirical results demonstrate the effectiveness of our proposed architecture, CoQE, in the single-value answer setting. It not only enhances ICL performance through improved representation learning, but also successfully reconciles ICL and IWL capabilities across synthetic few-shot classification and a newly designed pseudo-arithmetic task. Code: https://github.com/McGuinnessChen/dual-representation-space-encoding

cs.LG↗

arXiv2025

Exploring the Hidden Reasoning Process of Large Language Models by Misleading Them

Large language models (LLMs) have been able to perform various forms of reasoning tasks in a wide range of scenarios, but are they truly engaging in task abstraction and rule-based reasoning beyond mere memorization? To answer this question, we propose a novel experimental approach, Misleading Fine-Tuning (MisFT), to examine whether LLMs perform abstract reasoning by altering their original understanding of fundamental rules. In particular, by constructing datasets with math expressions or logical formulas that contradict correct principles, we fine-tune the model to learn those contradictory rules and assess its generalization ability on unseen test domains. Through a series of experiments, we find that current LLMs are capable of applying contradictory rules to solve practical math word problems and natural language reasoning tasks, implying the presence of an internal mechanism in LLMs that abstracts before reasoning.

cs.LG↗

arXiv2025

When Do Neural Networks Learn World Models?

Humans develop world models that capture the underlying generation process of data. Whether neural networks can learn similar world models remains an open problem. In this work, we present the first theoretical results for this problem, showing that in a multi-task setting, models with a low-degree bias provably recover latent data-generating variables under mild assumptions--even if proxy tasks involve complex, non-linear functions of the latents. However, such recovery is sensitive to model architecture. Our analysis leverages Boolean models of task solutions via the Fourier-Walsh transform and introduces new techniques for analyzing invertible Boolean transforms, which may be of independent interest. We illustrate the algorithmic implications of our results and connect them to related research areas, including self-supervised learning, out-of-distribution generalization, and the linear representation hypothesis in large language models.

cs.LG↗

arXiv2025

Exploring dynamical quantum phase transition from pure states to mixed states through extended Su-Schrieffer-Heeger models

We investigate dynamical quantum phase transitions (DQPTs) in both pure and mixed states within the extended SSH model framework, focusing on the SSH-3 and SSH-4 variants, which differ in symmetry properties. The SSH-3 model, characterized by a chiral-like point symmetry rather than true chiral symmetry, supports robust localized edge states tied to its topological nature. Our results show that for pure states, DQPTs occur after quenches crossing the topological transition, even when the energy band gap remains open. For mixed states, DQPT behavior aligns with pure states at low temperatures but undergoes significant changes at higher temperatures, including the emergence of multiple critical times. In contrast, the SSH-4 model, which possesses chiral symmetry, features four distinct energy spectrum configurations. We find that pure-state DQPTs arise only when the quench starts from a gapless initial state and crosses the critical topological point. At finite temperature, mixed-state DQPTs persist at low temperatures only if the corresponding pure-state quench induces DQPTs, but they disappear at elevated temperatures. These findings elucidate the interplay between symmetry, topology, and temperature in governing DQPTs within generalized SSH models.

quant-ph↗

arXiv2025

Multimodal machine learning with large language embedding model for polymer property prediction

Contemporary large language models (LLMs), such as GPT-4 and Llama, have harnessed extensive computational power and diverse text corpora to achieve remarkable proficiency in interpreting and generating domain-specific content, including materials science. To leverage the domain knowledge embedded within these models, we propose a simple yet effective multimodal architecture, PolyLLMem, which integrates text embeddings generated by Llama 3 with molecular structure embeddings derived from Uni-Mol, for polymer properties prediction tasks. In our model, Low-rank adaptation (LoRA) layers were also incorporated during the property prediction tasks to refine the embeddings based on our limited polymer dataset, thereby enhancing their chemical relevance for polymer SMILES representation. This balanced fusion of fine-tuned textual and structural information enables PolyLLMem to accurately predict a variety of polymer properties despite the scarcity of training data. Its performance is comparable to, and in some cases exceeds, that of graph-based models, as well as transformer-based models that typically require pretraining on millions of polymer samples. These findings demonstrate that LLM, such as Llama, can effectively capture chemical information encoded in polymer PSMILES, and underscore the efficacy of multimodal fusion of LLM embeddings and molecular structure embeddings in overcoming data scarcity and accelerating the discovery of advanced polymeric materials.

cs.LG↗

arXiv2025

A method of supervised learning from conflicting data with hidden contexts

Conventional supervised learning assumes a stable input-output relationship. However, this assumption fails in open-ended training settings where the input-output relationship depends on hidden contexts. In this work, we formulate a more general supervised learning problem in which training data is drawn from multiple unobservable domains, each potentially exhibiting distinct input-output maps. This inherent conflict in data renders standard empirical risk minimization training ineffective. To address this challenge, we propose a method LEAF that introduces an allocation function, which learns to assign conflicting data to different predictive models. We establish a connection between LEAF and a variant of the Expectation-Maximization algorithm, allowing us to derive an analytical expression for the allocation function. Finally, we provide a theoretical analysis of LEAF and empirically validate its effectiveness on both synthetic and real-world tasks involving conflicting data.

cs.LG↗

arXiv2025

Feature contamination: Neural networks learn uncorrelated features and fail to generalize

Learning representations that generalize under distribution shifts is critical for building robust machine learning models. However, despite significant efforts in recent years, algorithmic advances in this direction have been limited. In this work, we seek to understand the fundamental difficulty of out-of-distribution generalization with deep neural networks. We first empirically show that perhaps surprisingly, even allowing a neural network to explicitly fit the representations obtained from a teacher network that can generalize out-of-distribution is insufficient for the generalization of the student network. Then, by a theoretical study of two-layer ReLU networks optimized by stochastic gradient descent (SGD) under a structured feature model, we identify a fundamental yet unexplored feature learning proclivity of neural networks, feature contamination: neural networks can learn uncorrelated features together with predictive features, resulting in generalization failure under distribution shifts. Notably, this mechanism essentially differs from the prevailing narrative in the literature that attributes the generalization failure to spurious correlations. Overall, our results offer new insights into the non-linear feature learning dynamics of neural networks and highlight the necessity of considering inductive biases in out-of-distribution generalization.

cs.LG↗

arXiv2024

Preserving Silent Features for Domain Generalization

Domain generalization (DG) aims to improve the generalization ability of the model trained on several known training domains over unseen test domains. Previous work has shown that self-supervised contrastive pre-training improves the robustness of the model on downstream tasks. However, in this paper, we find that self-supervised models do not exhibit better generalization performance than supervised models pre-trained on the same dataset in the DG setting. We argue that this is owing to the fact that the richer intra-class discriminative features extracted by self-supervised contrastive learning, which we term silent features, are suppressed during supervised fine-tuning. These silent features are likely to contain features that are more generalizable on the test domain. In this work, we model and analyze this feature suppression phenomenon and theoretically prove that preserving silent features can achieve lower expected test domain risk under certain conditions. In light of this, we propose a simple yet effective method termed STEP (Silent Feature Preservation) to improve the generalization performance of the self-supervised contrastive learning pre-trained model by alleviating the suppression of silent features during the supervised fine-tuning process. Experimental results show that STEP exhibits state-of-the-art performance on standard DG benchmarks with significant distribution shifts.

cs.LG↗

arXiv2022

Adjacency constraint for efficient hierarchical reinforcement learning

Goal-conditioned Hierarchical Reinforcement Learning (HRL) is a promising approach for scaling up reinforcement learning (RL) techniques. However, it often suffers from training inefficiency as the action space of the high-level, i.e., the goal space, is large. Searching in a large goal space poses difficulty for both high-level subgoal generation and low-level policy learning. In this paper, we show that this problem can be effectively alleviated by restricting the high-level action space from the whole goal space to a $k$-step adjacent region of the current state using an adjacency constraint. We theoretically prove that in a deterministic Markov Decision Process (MDP), the proposed adjacency constraint preserves the optimal hierarchical policy, while in a stochastic MDP the adjacency constraint induces a bounded state-value suboptimality determined by the MDP's transition structure. We further show that this constraint can be practically implemented by training an adjacency network that can discriminate between adjacent and non-adjacent subgoals. Experimental results on discrete and continuous control tasks including challenging simulated robot locomotion and manipulation tasks show that incorporating the adjacency constraint significantly boosts the performance of state-of-the-art goal-conditioned HRL approaches.

cs.LG↗

arXiv2022

Learning Invariable Semantical Representation from Language for Extensible Policy Generalization

Recently, incorporating natural language instructions into reinforcement learning (RL) to learn semantically meaningful representations and foster generalization has caught many concerns. However, the semantical information in language instructions is usually entangled with task-specific state information, which hampers the learning of semantically invariant and reusable representations. In this paper, we propose a method to learn such representations called element randomization, which extracts task-relevant but environment-agnostic semantics from instructions using a set of environments with randomized elements, e.g., topological structures or textures, yet the same language instruction. We theoretically prove the feasibility of learning semantically invariant representations through randomization. In practice, we accordingly develop a hierarchy of policies, where a high-level policy is designed to modulate the behavior of a goal-conditioned low-level policy by proposing subgoals as semantically invariant representations. Experiments on challenging long-horizon tasks show that (1) our low-level policy reliably generalizes to tasks against environment changes; (2) our hierarchical policy exhibits extensible generalization in unseen new tasks that can be decomposed into several solvable sub-tasks; and (3) by storing and replaying language trajectories as succinct policy representations, the agent can complete tasks in a one-shot fashion, i.e., once one successful trajectory has been attained.

cs.CL↗

arXiv2021

CRIL: Continual Robot Imitation Learning via Generative and Prediction Model

Imitation learning (IL) algorithms have shown promising results for robots to learn skills from expert demonstrations. However, they need multi-task demonstrations to be provided at once for acquiring diverse skills, which is difficult in real world. In this work we study how to realize continual imitation learning ability that empowers robots to continually learn new tasks one by one, thus reducing the burden of multi-task IL and accelerating the process of new task learning at the same time. We propose a novel trajectory generation model that employs both a generative adversarial network and a dynamics-aware prediction model to generate pseudo trajectories from all learned tasks in the new task learning process. Our experiments on both simulation and real-world manipulation tasks demonstrate the effectiveness of our method.

cs.RO↗

arXiv2021

Generating Adjacency-Constrained Subgoals in Hierarchical Reinforcement Learning

Goal-conditioned hierarchical reinforcement learning (HRL) is a promising approach for scaling up reinforcement learning (RL) techniques. However, it often suffers from training inefficiency as the action space of the high-level, i.e., the goal space, is often large. Searching in a large goal space poses difficulties for both high-level subgoal generation and low-level policy learning. In this paper, we show that this problem can be effectively alleviated by restricting the high-level action space from the whole goal space to a $k$-step adjacent region of the current state using an adjacency constraint. We theoretically prove that the proposed adjacency constraint preserves the optimal hierarchical policy in deterministic MDPs, and show that this constraint can be practically implemented by training an adjacency network that can discriminate between adjacent and non-adjacent subgoals. Experimental results on discrete and continuous control tasks show that incorporating the adjacency constraint improves the performance of state-of-the-art HRL approaches in both deterministic and stochastic environments.

cs.LG↗