arXiv subjects

Ruihan Guo

Publications and source records attributed to Ruihan Guo.

15 recordsLinked to original sources

arXiv2026

Batched Contextual Reinforcement II: Does RLVR Need Long Rollout Windows?

Long rollout windows make reinforcement learning with verifiable rewards (RLVR) expensive, yet simply shortening them can remove the correctness signal: when every single-problem rollout truncates before an answer, group-relative accuracy advantages vanish. As a technical continuation of Batched Contextual Reinforcement (BCR), we study how concurrent rewards relax this dependence on long windows. Concurrent Constraint Reinforcement (CCR) places three independently verifiable problems in one capped training completion. Correct answers completed before truncation retain credit, while a shared budget encourages shorter useful reasoning without an explicit length penalty. We connect this mechanism to conditional reward- and update-variance analyses and study 4B and 8B mathematical reasoning models. Against single-problem GRPO with a 32k window, CCR with an 8,000-token window reduces tokens per training step from 975,464 to 174,957 on 4B and from 793,832 to 165,788 on 8B, saving 82.1% and 79.1%, respectively. An 8B training trace shows increasing accuracy reward alongside shorter completions. Single-problem evaluations provide supporting evidence of retained reasoning quality. These results identify reward-preserving training structure as a practical route to lower per-step cost in short-window RLVR.

cs.LG↗

arXiv2026

JUICE: Unified Multimodal Modeling in Pretrained Representation Spaces

Most unified multimodal models treat images and text asymmetrically: a pretrained language model generates text, an attached diffusion head generates images, and outputs that contain both are produced in a fixed order, so the first output cannot adapt to the second. We ask whether both modalities can instead be generated by one process that is trained on them jointly from scratch. Pretrained encoder spaces hold both modalities in one continuous form and carry knowledge learned at scale, and recent work finds them effective as generative targets for vision and language. We therefore model the joint distribution directly in these spaces. We introduce JUICE (Joint Unified multimodal modeling In Continuous Encoder spaces), a single flow matching Transformer over frozen image and text representations, in which each modality has its own noise level. Which modalities are clean and which are generated then decides the task: image generation, captioning, visual question answering, or joint generation. Controlled pretraining runs test each design choice. At equal guidance, generating text as continuous states leaves image generation intact (48.41 GenEval, against 47.86 for a model trained only for text-to-image generation), while captions lose some exact wording. Training on joint and conditional denoising together beats either alone, and semantic encoder spaces beat VAE latents and raw pixels as targets. At 2.1B parameters, with no language model initialization and at 224x224, JUICE reaches up to 0.88 on GenEval and 73.1 on VQAv2. By sampling both modalities from the joint distribution (coupled sampling), it can also draw a route on a map while writing out the matching moves. On mazes with several valid solutions, joint success rises from 54.6% with independent sampling to 93.7%, and no modality has to go first. On visual spatial planning, JUICE solves 99.8% of maps at its training sizes.

cs.CV↗

arXiv2026

How Much Can Language Models Gain from Test-Time Computation?

How much can test-time computation improve a language model, and at what cost? Test-time scaling is widely proposed as a substitute for larger models, but existing comparisons mostly evaluate one domain at a time and rarely charge selection to the budget. We introduce SELF-POT, a benchmark and evaluation framework that measures the test-time potential of a model across competition mathematics, competitive programming, and agentic workflows. SELF-POT separates candidate coverage from final accuracy on static tasks, tracks correctness transitions under revision, and measures protocol completion alongside task success in agentic environments. Under a unified budget rule, it compares Direct inference with parallel sampling and self-revision under fixed multiples of the Direct budget, and charges every model call, including selection and critique, in dollars. This design supports two kinds of comparison: the gain a model obtains from additional inference, and a lower-cost model with additional inference against a stronger model. Across five low-cost reasoning models on 350 sealed tasks, with Claude Opus 5.5 Direct as the reference, the returns depend on the domain, the selection rule, and failure handling. When we replay the retained programming candidate pools, public-example selection raises correct submissions from 376 to 453 of 500 scheduled cells while saving 12-49% of logical API cost across models, and simply retaining an available candidate when judging fails recovers 61 submissions at unchanged cost. On identical mathematics pools, judging with fallback yields 186 correct submissions versus 182 for voting, while voting saves 12-21% of logical API cost. These controlled replays show how selection and failure handling change the gains realized from the same generated candidates, and they quantify the marginal value of a model judge.

cs.LG↗

arXiv2026

Does Scaling Reinforcement Learning Really Require More Training?

Scaling reasoning typically spends more compute on reinforcement learning (RL) or on inference. We show that a completed RL training history can yield policies stronger than the checkpoints visited by its optimizer. We call this policy-space scaling: expanding the deployable policy set accessible from a fixed RL history, without extending training or increasing per-query inference computation. We instantiate it with SURGE (Scaling Up RL Gradient-free via Eigenspace fusion). SURGE combines two checkpoints from the same RL run: a high-accuracy anchor and a competitive donor that generates shorter responses. It expresses both checkpoints as changes from their shared initialization, then spectrally decomposes the anchor's update to retain its dominant component and incorporate the donor's complementary component. With a fixed target for how much of the anchor update to retain, SURGE determines the block size from the weights without testing candidate policies. We evaluate two 1.5B mathematical-reasoning histories, DeepSeek and Nemotron, and one 7B coding history, OLMo. SURGE improves benchmark-average accuracy over both input checkpoints while using fewer reasoning tokens than the anchor. It reaches 54.17% on DeepSeek AIME24 against a measured native maximum of 50.83%, and 83.7% on OLMo HumanEval+ against 82.8%. These gains exceed the observed training curves. Geometric controls support the importance of RL-update structure beyond weight displacement or token reduction alone. Each constructed model runs as a single policy. Our findings identify stored RL history as a reusable scaling resource: the capability available from a training run need not end at its best checkpoint.

cs.LG↗

arXiv2026

ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning

Protein generative models have shown remarkable promise in protein design, yet their success rates remain constrained by reliance on curated sequence-structure datasets and by misalignment between supervised objectives and real design goals. We present ProteinZero, an online reinforcement learning framework for inverse folding models that enables scalable, automated, and continuous self-improvement with computationally efficient feedback. ProteinZero employs a reward pipeline that combines structural guidance from ESMFold with a novel self-derived ddG predictor, providing stable multi-objective signals while avoiding the prohibitive cost of physics-based methods. To ensure robustness in online RL, we further introduce a novel embedding-level diversity regularizer that mitigates mode collapse and promotes sequence-level diversity among generated designs. Within a general RL formulation balancing multi-reward optimization, KL-divergence from a reference model, and diversity regularization, ProteinZero achieves robust improvements across designability, predicted stability, recovery, and diversity. On the CATH-4.3 benchmark, it consistently outperforms state-of-the-art baselines including ProteinMPNN, ESM-IF, and InstructPLM, reducing design failure rates by 36-48% and achieving success rates above 90% across diverse folds. Importantly, a complete RL run can be executed on a single 8xGPU node within three days, including reward computation and data generation. These results indicate that efficient online RL fine-tuning can complement supervised pretraining by allowing protein generative models to evolve continuously from their own outputs and optimize multiple design objectives without labeled data, opening new possibilities for exploring the vast protein design space. Code and model checkpoints are available at https://github.com/ziwenwang28/ProteinZero.

cs.LG↗

arXiv2026

Can Large Language Models Derive New Knowledge? A Dynamic Benchmark for Biological Knowledge Discovery

Recent advancements in Large Language Model (LLM) agents have demonstrated remarkable potential in automatic knowledge discovery. However, rigorously evaluating an AI's capacity for knowledge discovery remains a critical challenge. Existing benchmarks predominantly rely on static datasets, leading to inevitable data contamination where models have likely seen the evaluation knowledge during training. Furthermore, the rapid release cycles of modern LLMs render static benchmarks quickly outdated, failing to assess the ability to discover truly new knowledge. To address these limitations, we propose DBench-Bio, a dynamic and fully automated benchmark designed to evaluate AI's biological knowledge discovery ability. DBench-Bio employs a three-stage pipeline: (1) data acquisition of rigorous, authoritative paper abstracts; (2) QA extraction utilizing LLMs to synthesize scientific hypothesis questions and corresponding discovery answers; and (3) QA filter to ensure quality based on relevance, clarity, and centrality. We instantiate this pipeline to construct a monthly-updated benchmark covering 12 biomedical sub-domains. Extensive evaluations of SOTA models reveal current limitations in discovering new knowledge. Our work provides the first dynamic, automatic framework for assessing the new knowledge discovery capabilities of AI systems, establishing a living, evolving resource for AI research community to catalyze the development of knowledge discovery.

cs.CL↗

arXiv2026

Variable-Length Generative Protein Design via Generalized Poisson Flow

The ability to generate variable-length proteins is crucial in protein design, where the optimal length is often unknown and tightly coupled to designability. Current diffusion- and flow-based generative models typically require the protein length to be specified before sampling, limiting their flexibility in exploring the feasible design space. To address this limitation, we introduce Generalized Poisson Flow (GPFlow), a variable-length generative framework that learns the rate function of an inhomogeneous generalized Poisson process by minimizing its negative log-likelihood. We establish population-level guarantees for recovering the joint multimodal distribution and derive an upper bound on the KL divergence between the data and generated distributions. We comprehensively evaluate GPFlow across structure and sequence design, motif scaffolding, and peptide co-design, spanning Euclidean, categorical, and Riemannian modalities to fully validate its variable-length generation quality. In unconditional design, GPFlow improves structural designability and achieves the best distributional fitness for sequence design compared to their corresponding fixed-length baselines, while perfectly recovering the length distribution. In conditional motif scaffolding, GPFlow ranks first on 10 of 16 structure-based design tasks with significantly more unique successes and also achieves more passed tasks in sequence-based design. In peptide co-design, GPFlow remains competitive even without access to a native-length oracle.

cs.LG↗

arXiv2026

LangFlow: Continuous Diffusion Rivals Discrete in Language Modeling

Continuous diffusion has been the foundation of high-fidelity, controllable, and few-step generation of many data modalities such as images. However, in language modeling, prior continuous diffusion language models (DLMs) lag behind discrete counterparts due to the sparse data space and the underexplored design space. In this work, we close this gap with LangFlow, the first continuous DLM to rival discrete diffusion, by connecting embedding-space DLMs to Flow Matching via Bregman divergence, alongside three key innovations: (1) we derive a novel ODE-based NLL bound for principled evaluation of continuous flow-based language models; (2) we propose an information-uniform principle for setting the noise schedule, which motivates a learnable noise scheduler based on a Gumbel distribution; and (3) we revise prior training protocols by incorporating self-conditioning, as we find it improves both likelihood and sample quality of embedding-space DLMs with effects substantially different from discrete diffusion. Putting everything together, LangFlow rivals top discrete DLMs on both the perplexity (PPL) and the generative perplexity (Gen. PPL), reaching a PPL of 30.0 on LM1B and 24.6 on OpenWebText. It even exceeds autoregressive baselines in zero-shot transfer on 4 out of 7 benchmarks. LangFlow provides the first clear evidence that continuous diffusion is a promising paradigm for language modeling. Homepage: https://github.com/nealchen2003/LangFlow

cs.CL↗

arXiv2026

M3: High-fidelity Text-to-Image Generation via Multi-Modal, Multi-Agent and Multi-Round Visual Reasoning

Generative models have achieved impressive fidelity in text-to-image synthesis, yet struggle with complex compositional prompts involving multiple constraints. We introduce \textbf{M3 (Multi-Modal, Multi-Agent, Multi-Round)}, a training-free framework that systematically resolves these failures through iterative inference-time refinement. M3 orchestrates off-the-shelf foundation models in a robust multi-agent loop: a Planner decomposes prompts into verifiable checklists, while specialized Checker, Refiner, and Editor agents surgically correct constraints one at a time, with a Verifier ensuring monotonic improvement. Applied to open-source models, M3 achieves remarkable results on the challenging OneIG-EN benchmark, with our Qwen-Image+M3 surpassing commercial flagship systems including Imagen4 (0.515) and Seedream 3.0 (0.530), reaching state-of-the-art performance (0.532 overall). This demonstrates that intelligent multi-agent reasoning can elevate open-source models beyond proprietary alternatives. M3 also substantially improves GenEval compositional metrics, effectively doubling spatial reasoning performance on hardened test sets. As a plug-and-play module compatible with any pre-trained T2I model, M3 establishes a new paradigm for compositional generation without costly retraining.

cs.CV↗

arXiv2025

Phase-Field Modeling and Energy-Stable Schemes for Osmotic Flow through Semi-Permeable

We present a thermodynamically consistent phase-field model for simulating fluid transport across semi-permeable membranes, with a particular focus on osmotic pressure effects. The model extends the classical Navier-Stokes-Cahn-Hilliard (NSCH) system by introducing an Allen-Cahn-type transmembrane flux governed by chemical potential imbalances, resulting in a strongly coupled system involving fluid motion, solute transport, and interface dynamics. To solve this system efficiently and accurately, we develop high-order, energy-stable numerical schemes. The local discontinuous Galerkin (LDG) method is employed for spatial discretization, offering high-order accuracy and geometric flexibility. For temporal integration, we first construct a first-order decoupled scheme with rigorous energy stability, and then improve temporal accuracy via a semi-implicit spectral deferred correction (SDC) method. Numerical experiments confirm the theoretical properties of the proposed scheme and demonstrate the influence of osmotic pressure and membrane permeability on droplet morphology at equilibrium. The framework offers a robust and versatile tool for modeling transmembrane fluid transport in both biological and industrial applications.

physics.flu-dyn↗

arXiv2025

Hotspot-Driven Peptide Design via Multi-Fragment Autoregressive Extension

Peptides, short chains of amino acids, interact with target proteins, making them a unique class of protein-based therapeutics for treating human diseases. Recently, deep generative models have shown great promise in peptide generation. However, several challenges remain in designing effective peptide binders. First, not all residues contribute equally to peptide-target interactions. Second, the generated peptides must adopt valid geometries due to the constraints of peptide bonds. Third, realistic tasks for peptide drug development are still lacking. To address these challenges, we introduce PepHAR, a hot-spot-driven autoregressive generative model for designing peptides targeting specific proteins. Building on the observation that certain hot spot residues have higher interaction potentials, we first use an energy-based density model to fit and sample these key residues. Next, to ensure proper peptide geometry, we autoregressively extend peptide fragments by estimating dihedral angles between residue frames. Finally, we apply an optimization process to iteratively refine fragment assembly, ensuring correct peptide structures. By combining hot spot sampling with fragment-based extension, our approach enables de novo peptide design tailored to a target protein and allows the incorporation of key hot spot residues into peptide scaffolds. Extensive experiments, including peptide design and peptide scaffold generation, demonstrate the strong potential of PepHAR in computational peptide binder design. Source code will be available at https://github.com/Ced3-han/PepHAR.

q-bio.BM↗

arXiv2024

FAFE: Immune Complex Modeling with Geodesic Distance Loss on Noisy Group Frames

Despite the striking success of general protein folding models such as AlphaFold2(AF2, Jumper et al. (2021)), the accurate computational modeling of antibody-antigen complexes remains a challenging task. In this paper, we first analyze AF2's primary loss function, known as the Frame Aligned Point Error (FAPE), and raise a previously overlooked issue that FAPE tends to face gradient vanishing problem on high-rotational-error targets. To address this fundamental limitation, we propose a novel geodesic loss called Frame Aligned Frame Error (FAFE, denoted as F2E to distinguish from FAPE), which enables the model to better optimize both the rotational and translational errors between two frames. We then prove that F2E can be reformulated as a group-aware geodesic loss, which translates the optimization of the residue-to-residue error to optimizing group-to-group geodesic frame distance. By fine-tuning AF2 with our proposed new loss function, we attain a correct rate of 52.3\% (DockQ $>$ 0.23) on an evaluation set and 43.8\% correct rate on a subset with low homology, with substantial improvement over AF2 by 182\% and 100\% respectively.

q-bio.QM↗

arXiv2024

Full-Atom Peptide Design based on Multi-modal Flow Matching

Peptides, short chains of amino acid residues, play a vital role in numerous biological processes by interacting with other target molecules, offering substantial potential in drug discovery. In this work, we present PepFlow, the first multi-modal deep generative model grounded in the flow-matching framework for the design of full-atom peptides that target specific protein receptors. Drawing inspiration from the crucial roles of residue backbone orientations and side-chain dynamics in protein-peptide interactions, we characterize the peptide structure using rigid backbone frames within the $\mathrm{SE}(3)$ manifold and side-chain angles on high-dimensional tori. Furthermore, we represent discrete residue types in the peptide sequence as categorical distributions on the probability simplex. By learning the joint distributions of each modality using derived flows and vector fields on corresponding manifolds, our method excels in the fine-grained design of full-atom peptides. Harnessing the multi-modal paradigm, our approach adeptly tackles various tasks such as fix-backbone sequence design and side-chain packing through partial sampling. Through meticulously crafted experiments, we demonstrate that PepFlow exhibits superior performance in comprehensive benchmarks, highlighting its significant potential in computational peptide design and analysis.

q-bio.BM↗

arXiv2022

Learning Long-Term Reward Redistribution via Randomized Return Decomposition

Many practical applications of reinforcement learning require agents to learn from sparse and delayed rewards. It challenges the ability of agents to attribute their actions to future outcomes. In this paper, we consider the problem formulation of episodic reinforcement learning with trajectory feedback. It refers to an extreme delay of reward signals, in which the agent can only obtain one reward signal at the end of each trajectory. A popular paradigm for this problem setting is learning with a designed auxiliary dense reward function, namely proxy reward, instead of sparse environmental signals. Based on this framework, this paper proposes a novel reward redistribution algorithm, randomized return decomposition (RRD), to learn a proxy reward function for episodic reinforcement learning. We establish a surrogate problem by Monte-Carlo sampling that scales up least-squares-based reward redistribution to long-horizon problems. We analyze our surrogate loss function by connection with existing methods in the literature, which illustrates the algorithmic properties of our approach. In experiments, we extensively evaluate our proposed method on a variety of benchmark tasks with episodic rewards and demonstrate substantial improvement over baseline algorithms.

cs.LG↗

arXiv2016

A p-adaptive local discontinuous galerkin level set method for Willmore flow

The level set method is often used to capture interface behavior in two or three dimensions. In this paper, we present a combination of local discontinuous Galerkin (LDG) method and level set method for simulating Willmore flow. The LDG scheme is energy stable and mass conservative, which are good properties comparing with other numerical methods. In addition, to enhance the efficiency of the proposed LDG scheme and level set method, we employ a p-adaptive local discontinuous Galerkin technique, which applies high order polynomial approximations around the zero level set and low order ones away from the zero level set. A major advantage of the level set method is that the topological changes are well defined and easily performed. In particular, given the stiffness of Willmore flow, a high order semi-implicit Runge-Kutta method is employed for time discretization, which allows larger time step. The equations at the implicit time level are linear, we demonstrate an efficient and practical multi-grid solver to solve the equations. Numerical examples are given to illustrate the combination of the LDG scheme and level set method provides an efficient and practical approach when simulating the Willmore flow.

math.NA↗