Searcharxiv⌕ Search

arXiv subjects

Jialin Liu

Publications and source records attributed to Jialin Liu.

At least 19 recordsLinked to original sources

AutoRL: A Multi-Agent System towards Autonomous Reinforcement Learning

Recursive self-improvement (RSI) is one of the most promising paths toward an AI singularity for superintelligence. Achieving this vision requires AI systems to undertake the full training pipeline for iterative improvement. Reinforcement learning (RL) plays an essential role in this cycle to improve model capabilities and generalization, yet automating RL remains difficult due to unstable training dynamics and the need for sustained supervision. We introduce AutoRL, a multi-agent system for automating RL training, as a cornerstone for future RSI. Different from conducting research by end-to-end complete experiments, AutoRL monitors the evolving training state and integrates process-level supervision and research into an ongoing RL training, following the practical workflow of an RL researcher. Specifically, AutoRL consists of three RL-specific agentic roles. Perceptors track training dynamics, rollouts, evaluation, and efficiency, triggering deliberation when they detect anomalies, degradation, or stagnation. Three complementary Proposers diagnose problems and refine candidate interventions through shared evidence and checks. The Orchestrator reviews their recommendation and applies approved changes through online hot updates or checkpoint-based resumption. Experiments on Qwen3 and LongCat-Flash-Lite demonstrate the superiority of AutoRL over static RL recipes and a general agent. The research records show that existing agents can handle unattended RL supervision and dynamic adjustment. The difficulty for future RSI lies in developing fundamental methods that are valuable for resource-consuming validation.

cs.AI↗

Taste or Strategy? Nationalistic Bias and Competitor Penalties in Figure Skating Judging

Many decisions rest on expert panels whose members have ties to some candidates, and favoritism is hard to tell from shared taste or better information. Using a rich dataset from figure skating, we find evidence of a strategic compatriot premium and a targeted penalty on the compatriot's close rivals. The premium falls along a randomly drawn start order and, before 2022/23, rises when close rivals have their own judges on the panel. The penalty grows with the compatriot's placement chances and fades once she is out of contention. A counterfactual analysis shows that these biases can shape close competitions.

econ.GN↗

Turán problems with bounded matching number in $k$-uniform hypergraphs

For a family $\mathcal{F}$ of $k$-graphs, $ex_k(n,\mathcal{F})$ denotes the maximum number of edges in an $n$-vertex $\mathcal{F}$-free $k$-graph. Let $M_{s+1}^k$ denote a matching of size $s+1$ in $k$-uniform hypergraphs. Recently, Alon and Frankl (JCTB, 2024) determined $ex_2(n,\{M_{s+1}^2,K_{\ell+1}\})$ for all $n\geq 2s+1$ and $\ell\geq 2$. For every non-bipartite graph $F$, Gerbner (JGT, 2024) determined $ex_2(n,\{M_{s+1}^2,F\})$ for sufficiently large $n$. In this paper, we investigate this problem for different ranges of the matching parameter. First we prove that for every graph $F$ with $χ(F)>3$, there exist constants $β>0$ and $s_0$ such that $ex_2(n,\{M^2_{s+1}, F\})=ex_2(2s+1,F)$ for $\max\{s_0,n/2-βn\}<s<n/2$. For integers $\ell\ge k\ge3$, let $\mathcal{K}_{\ell+1}^k$ be the family of all $k$-graphs $F$ with at most $\binom{\ell+1}{2}$ edges for which there is an $(\ell+1)$-set $L$ such that every pair of vertices of $L$ is covered by an edge of $F$, and let $H_{\ell+1}^k$ be the $k$-uniform hypergraph obtained from the complete graph $K_{\ell+1}$ by enlarging each edge with a set of $k-2$ new vertices, which is a member of $\mathcal{K}_{\ell+1}^k$. We determine $ex_k\bigl(n,\mathcal{K}_{\ell+1}^k\cup\{M_{s+1}^k\}\bigr)$ for $s< \frac{n}{8(k-1)^{k-2}(\ell-1)^3}$. For sufficiently large $s$, we also determine $ex_k\bigl(n,\{M_{s+1}^k,H_{\ell+1}^k\}\bigr)$ for $\frac{n}{k}-βn<s\leq \frac{n-k}{k}$ and $s< \frac{n}{8(k-1)^{k-2}(\ell-1)^3}$.

math.CO↗

Multi-Attractor GNNs: Set-Valued Expressivity Beyond Unique Equilibria

Recurrent and equilibrium graph neural networks (GNNs) often enforce a unique fixed point or use one training target per graph. Yet many combinatorial and scientific problems admit multiple valid solutions, with no preferred one. A designated target can then impose an arbitrary selection rule. For tasks invariant to node relabeling, a symmetric graph may have a symmetric solution set but no symmetric solution. We show that multiple equilibria enable one weight-tied message-passing GNN to represent set-valued equivariant maps: different initializations approach different valid solutions. Under stated regularity assumptions, we first construct globally Lipschitz, permutation-equivariant dynamics that converge almost surely to valid solutions and reach every solution branch with positive probability. We then establish approximate realization by recurrent message passing with continuous component maps, with arbitrarily small update and limiting errors and arbitrarily high probability. This goes beyond standard universality arguments: although message passing alone cannot distinguish symmetric nodes, the evolving state keeps nodes distinguishable at every finite step without auxiliary node identifiers. Such dynamics can be learned without solution labels using problem-specific energies. On Ising ground states, structural module detection in protein graphs, and chemical reaction steady states, the learned updates produce multiple high-quality predictions with high numerical convergence rates. They achieve better average solution quality than the tested unique-equilibrium, single-target, and feedforward baselines, while remaining competitive with much larger diffusion-based solvers.

cs.LG↗

Learned Preconditioning for a Primal-Dual Interior-Point Method

Interior-point methods (IPMs) are among the most widely used algorithms for constrained optimization, yet their Newton-based search directions require costly second-order information and large linear-system solves. Learning to optimize offers cheaper updates learned from data, but the singular behavior of logarithmic barriers near constraint boundaries makes IPMs highly sensitive to perturbations, complicating both warm starting and learning reliable updates. We introduce pdLIP, an IPM for smooth nonlinear programs that integrates learned preconditioning with pdProj, an all-shifted primal-dual projected-search IPM. A shared coordinate-wise recurrent network predicts a positive diagonal preconditioner that scales the right-hand side of the reduced Newton system for the primal step, and the remaining slack and multiplier directions are recovered analytically. The learned iterations avoid Hessian evaluations and Newton-system solves, using only first-order and coordinate-wise operations amenable to GPU parallelization. Training is self-supervised, with a loss based on a penalty-barrier merit function and the residual of perturbed optimality conditions, requiring neither target directions nor precomputed solutions. Primal and dual shifts mitigate the barrier's sensitivity to perturbations near constraint boundaries, enabling effective warm starting. Across four classes of 200-dimensional convex and nonconvex constrained problems, pdLIP warm starts reduce pdProj refinement iterations by 63-67% compared with cold starts at the same KKT residual tolerance of $10^{-8}$, with negligible warm-start generation cost relative to the subsequent pdProj solve. Improvements persist on box-constrained QPs with 1000 variables and extend to applications including portfolio optimization, support vector machines, and a nonlinear control example.

math.OC↗

DAFNet: Dual-path Adaptive Fusion Network for High-Fidelity Cross-Modality Brain MR Image Synthesis

Cross-modality MRI synthesis using deep learning can streamline clinical workflows, compensate for missing image contrasts, and reduce examination time; however, existing methods often require substantial computational resources, limiting their practical accessibility. To address this limitation, we propose and investigate a lightweight yet effective framework, termed the Dual-path Adaptive Fusion Network (DAFNet), for T1-to-T2 images synthesis. DAFNet is based on cGAN (conditional generative adversarial networks) structure, and the generator employs a dual-path encoder that adaptively combines depth-wise separable convolutions and dilated convolutions to capture both fine-grained details and broader contextual features. A novel Dual-path Adaptive Fusion Module (DAFM) is introduced to dynamically combine these feature streams through channel-wise complementary weighting, enabling efficient and adaptive feature integration. This fusion mechanism is further applied to the final skip connection to enhance reconstruction fidelity, while the decoder adopts a standard transposed convolution architecture. Coupled with a conventional conditional GAN discriminator, the proposed model maintains low computational complexity while improving perceptual image fidelity. Experimental results demonstrate that DAFNet achieves superior performance compared with baseline U-Net and conventional cGAN models, reaching a peak signal-to-noise ratio (PSNR) of 26.43 dB while significantly reducing model size. This result indicates that DAFNet provides an effective balance between synthesis fidelity and computational efficiency, making it a promising solution for deployment on standard computing hardware and for broader clinical and research applications in MRI contrast synthesis.

physics.med-ph↗

PostCam: Camera-Controllable Novel-View Video Generation with Query-Shared Cross-Attention

We propose PostCam, a streamlined framework for novel-view video generation that achieves superior detail preservation and precise camera trajectory editing in dynamic scenes. Current methods often struggle with a trade-off between pose-based control, which lacks visual detail, and rendering-based guidance, which is overly sensitive to geometric accuracy. Despite recent hybrid attempts, achieving precise motion and visual consistency remains challenging due to the lack of effective cross-modal alignment. We argue that robust control stems from the deep alignment of multimodal signals rather than increased input complexity. Our core contribution is the Query-Shared Cross-Attention mechanism, which projects 6-DoF poses and rendered features into a unified latent space. This allows the model to spontaneously achieve intrinsic consistency between motion cues and pixel-level guidance during denoising. Experiments demonstrate that PostCam maintains high-fidelity visual details while outperforming state-of-the-art methods by 20% in trajectory precision, exhibiting superior robustness in complex dynamic scenes. Our project webpage is publicly available at: https://cccqaq.github.io/PostCam.github.io/

cs.CV↗

AI-Assisted Writing Is Growing Fastest Among Less Established Scientists in Non-English-Speaking Countries

The recent emergence of AI-assisted writing raises an important question: how is this new technology being adopted across the scientific community, and how does adoption vary across linguistic and professional contexts? We analyze over two million full-text biomedical publications from PubMed Central from 2021 to 2024 using a distribution-based framework to estimate AI-generated content. We found that, in biomedical publications, AI-generated content increased substantially after ChatGPT, with larger increases in publications from countries with lower English proficiency. Increases were also greater among scientists with fewer publications and citations, those at earlier career stages, and those at lower-ranked institutions. Prior AI research experience was associated with greater increases in AI-assisted writing, which were also modestly associated with greater increases in publication productivity. These findings show that AI-assisted writing is growing fastest among biomedical scientists who may have historically faced barriers, a pattern with potentially positive implications for equity in science.

cs.DL↗

Beyond Modality Harmony: Orthogonal Purification and Topology-Guided MoE for Conflict-Aware Multimodal Recommendation

Multimodal Recommender Systems (MRSs) typically rely on a flawed "modality harmony" assumption, presuming that multimodal features are inherently beneficial and strictly aligned with users' collaborative interaction patterns. However, modality-topology conflicts are ubiquitous in real-world scenarios due to deceptive visual clickbaits and mismatched semantics. Blindly integrating these noisy modalities inevitably pollutes the pristine collaborative space, causing severe representation distortion. To address this, we propose Orthogonal purification and topology-guided MoE for conflict-aware multimodal Recommendation (OrthoRec). At its core, OrthoRec introduces Collaborative-Guided Orthogonal Purification (CGOP), which geometrically decouples multimodal features into directions parallel and orthogonal to a pure collaborative anchor. By adaptively truncating the orthogonal noise with an energy-preserving normalization, CGOP rectifies deceptive semantic directions while preserving the modality's intrinsic representation capacity. Furthermore, we design a Topology-Aware Routing Mixture-of-Experts (TAR-MoE). Guided by the collaborative topology, TAR-MoE employs decoupled sigmoid gating to break the zero-sum bottleneck of traditional softmax attention, autonomously determining the injection scale for each purified modality. Finally, a safe-SSL objective is introduced to dynamically penalize the forced contrastive alignment of contradictory pairs. Experiments on three real-world Amazon datasets show that OrthoRec consistently outperforms competitive recent baselines and exhibits improved robustness under modality noise and item sparsity.

cs.IR↗

Advisor career stage and PhD advisee outcomes

PhD advisors are central to doctoral training, but their influence may vary across career stages. Early-, mid-, and late-career advisors may differ in research activity, mentoring capacity, professional networks and access to resources. However, little is known about how PhD advisor career stage is associated with PhD student development outcomes. Drawing on multiple large-scale datasets comprising 250,838 advisor-advisee pairs from 312 U.S. PhD-granting institutions, we examine the relationship between advisor career stage and PhD advisee outcomes in knowledge production, collaboration networks and academic career placement. We find that early-career PhD advisors are associated with advisees' higher research productivity and citation performance, more opportunities to engage in direct and intensive research collaboration, and greater likelihood of securing a faculty position. Mid- and late-career faculty, by contrast, appear to have advantages in providing network capital which students can inherit after graduation, training PhD advisees to produce disruptive research, and supporting them in securing faculty positions at top institutions. This study contributes to a more comprehensive understanding of the reproduction of scientific talent by revealing the role of advisor career stage in shaping this process. These findings have implications for doctoral applicants' decision-making and for institutional policymaking on PhD training, faculty support and faculty evaluation.

cs.CY↗

Scientific exploration, collaboration and labor division in the large language model era

Large language models (LLMs) have rapidly and significantly entered scientific workflows, but it remains unclear how their diffusion is associated with changes in scientists' strategies in research directions and team building. We link PubMed Central full text with OpenAlex publication and collaboration histories for 775,323 scientists and analyze CRediT contribution statements from 137,120 multi-author papers. After 2022, scientists increasingly published across more intellectually distant fields and entered fields in which they had not previously worked. These increases in interdisciplinarity and exploration were especially pronounced among established scientists and scientists from non-English-speaking low- and middle-income countries. Authors with stronger AI-writing signals were already more interdisciplinary and exploratory before the widespread adoption of LLMs, and the gap widened further after 2022 compared with authors with weaker AI-writing signals. Scientists' collaboration networks also became more interdisciplinary after 2022. Yet, among authors with stronger AI-writing signals, research interdisciplinarity was less closely tied to the disciplinary diversity of their collaborators. The division of labor within research teams also became more differentiated. Contributors on papers published after 2022 reported narrower role sets on average, coauthors shared fewer roles in common, and their role profiles became less rigid and more fluid. Software and validation roles increased, while conceptual and management roles decreased. These patterns suggest that team members are taking on more distinct responsibilities and may rely less on one another to perform research tasks. Overall, this study indicates that the LLM era coincides with a broader reorganization of scientific exploration, collaboration, and the division of labor.

cs.DL↗

Unleashing Multimodal Large Language Models for Training-free HOI Detection in the Wild

Human-object interaction detection (HOID) has traditionally been formulated as a supervised detection problem over predefined interaction categories. While such paradigms achieve strong performance on closed-set benchmarks, they fundamentally entangle interaction understanding with dataset-specific supervision, limiting their ability to generalize to open-world and compositional scenarios. Recent HOI detectors attempt to leverage MLLMs through prompting strategies to transfer interaction-specific knowledge. However, such prompt-based approaches primarily focus on extracting discriminative representations from pretrained models, while underexploring their inherent multimodal reasoning capabilities. As a result, they struggle to provide informative contextual reasoning for ambiguous and open-world interaction scenarios. In this work, we present AgentHOI, a training-free, agentic framework that transfers the generalist multimodal reasoning capabilities of foundation models to HOI detection in the wild. Instead of learning interaction classifiers, AgentHOI modularly orchestrates complementary vision foundation modules to perform open-ended semantic reasoning and spatial grounding in a coordinated manner. To address the challenges of incomplete interaction discovery and ambiguous localization in complex scenes, we introduce two key mechanisms: (1) Context-aware Multi-round Reasoning, which progressively refines interaction hypotheses to ensure exhaustive and compositional HOI discovery, and (2) Multifaceted Interaction Localization, which enhances grounding precision by generating instance-specific descriptions that integrate semantic, spatial, and appearance cues. Extensive experiments demonstrate that AgentHOI achieves superior performance over state-of-the-art supervised and weakly supervised methods in real-world settings, despite requiring no HOID data for training.

cs.CV↗

Motion Reinforces Appearance: RGB-Skeleton Gated Residual Fusion for Micro-Gesture Online Recognition

Micro-gesture analysis attracts increasing attention for inferring spontaneous emotion from subtle body movements. Micro-gesture online recognition, which localizes and classifies each gesture instance in untrimmed videos, is a core task in the 4th EI-MiGA-IJCAI Challenge. Compared with typical temporal action detection, MGR emphasizes the localization and classification of actions, requiring the model to output the start time, end time, and category of each micro-gesture. Moreover, since micro-gestures are highly spontaneous, relying solely on a single modality makes it difficult to capture the complete and accurate multi-modal cues. In this work, we propose DyFADet+, which extends DyFADet into a dual-stream RGB-skeleton framework. In our model, both modalities are projected into shared multi-scale temporal embeddings and fused through a gated residual module, which adaptively injects skeleton motion into the RGB representation rather than using naive concatenation. Finally, these fused features are decoded by a Dynamic TAD head for online classification and boundary regression. On the SMG dataset, our method achieves an F1 score of 40.88, ranking 2nd in the Micro-gesture Online Recognition track.

cs.CV↗

Uniboost: Global Coordination with Value Alignment for Fair and Efficient Traffic Allocation

With the rapid evolution of internet services, recommendation systems have become indispensable. In particular, the blending (re-ranking) stage plays a pivotal role in allocating traffic across diverse business objectives. However, existing approaches often suffer from coupled allocation plans, score inflation, and a lack of interpretability. To address these challenges, we propose Uniboost, a unified traffic allocation framework. Uniboost introduces a posterior value alignment mechanism that calibrates abstract model scores to anchor metrics with explicit business semantics, significantly enhancing interpretability. Furthermore, it employs an independent linear boosting paradigm to decouple complex weighting schemes, enabling precise attribution of each plan's contribution. We validate the effectiveness of Uniboost through online A/B tests and in-depth data analysis, demonstrating three key findings: 1) Reducing the overall weight of weighted scores effectively mitigates unintended business interference, yielding a more efficient micro-level traffic allocation strategy; 2) Post-hoc analyses and aggregated dashboards provide intuitive, macro-level insights that guide the design of the overall traffic allocation mechanism; 3) The proposed "Effective Completion Score" serves as an easily obtainable post-metric that offers a reliable anchor for content recommendation pipelines. Collectively, our experiments show that Uniboost not only improves traffic allocation efficiency and recommendation performance at the micro level but also provides macro-level guidance for system iteration. Thus, this work provides an efficient and controllable traffic regulation solution for large-scale industrial recommendation systems.

cs.IR↗

GVGAI-LLM: Evaluating Large Language Model Agents with Infinite Games

We introduce GVGAI-LLM, a video game benchmark for evaluating the reasoning and problem-solving capabilities of large language models (LLMs). Built on the General Video Game AI framework, it features a diverse collection of arcade-style games designed to test a model's ability to handle tasks that differ from most existing LLM benchmarks. The benchmark leverages a video game description language that enables the rapid creation of new games (including rules and levels), helping to prevent overfitting over time. Each game scene is represented by a compact set of ASCII characters, allowing for efficient processing by language models. GVGAI-LLM defines interpretable metrics, including meaningful step ratio, step efficiency, and overall score, to assess model behavior. Through zero-shot evaluations across 118 games with diverse challenges and skill depth, we reveal persistent limitations of LLMs in spatial reasoning and basic planning. Current models consistently exhibit spatial and logical errors, motivating structured prompting and spatial grounding techniques. Although these interventions lead to partial improvements, the benchmark remains very far from being solved. GVGAI-LLM serves as a reproducible testbed for advancing research on language model capabilities, with a particular emphasis on agentic behavior and spatial reasoning. Furthermore, its ability to generate infinite benchmarks, both manually and procedurally, provides a scalable framework for longitudinal evaluation.

cs.AI↗

Bifurcation Models: Learning Set-Valued Solution Maps with Weight-Tied Dynamics

Many scientific and combinatorial problems admit multiple correct solutions, not a single label. Standard supervised learning resolves this ambiguity by choosing one solution as the target, but this hidden selector can be arbitrary, discontinuous, and harder to learn than the underlying solution set. We study bifurcation models, a weight-tied dynamical view in which different initializations can converge to different stable equilibria, so the model represents an attractor landscape rather than one chosen branch. We prove that broad set-valued maps with locally Lipschitz branches can be represented by regular equilibrium dynamics and that the induced selectors are almost everywhere regular, while manual selectors can be arbitrarily irregular. Experiments on frustrated Ising models show that such dynamics can discover multiple valid equilibria without branch labels and outperform single-branch supervision. Allen--Cahn experiments further show that diversity is not automatic: it can be encouraged explicitly, but with an accuracy--diversity tradeoff.

cs.LG↗

Keep Rehearsing and Refining: Lifelong Learning Vehicle Routing under Continually Drifting Tasks

Existing neural solvers for vehicle routing problems (VRPs) are typically trained either in a one-off manner on a fixed set of pre-defined tasks or in a lifelong manner with tasks arriving sequentially, assuming sufficient training on each task. Both settings overlook a common real-world property: problem patterns may drift continually over time, yielding massive tasks sequentially arising, each with only limited training resources. In this paper, we propose a novel lifelong learning paradigm for neural VRP solvers under continual task drift over time, where each task is locally stationary at one learning time step but receives only insufficient training resources. We empirically demonstrate that such continual drift arises in practice using a real-world logistics dataset. We then propose Dual Replay with Experience Enhancement (DREE), a general framework to improve learning efficiency and mitigate catastrophic forgetting under such drift. Extensive experiments based on both the real-world logistics dataset and commonly used synthetic dataset show that, under such continual drift, DREE effectively learns new tasks, preserves prior knowledge, improves generalization to unseen tasks, and can be applied to various existing neural solvers.

cs.LG↗

InSpatio-WorldFM: An Open-Source Real-Time Generative Frame Model

We present InSpatio-WorldFM, an open-source real-time frame model for spatial intelligence. Unlike video-based world models that rely on sequential frame generation and incur substantial latency due to window-level processing, InSpatio-WorldFM adopts a frame-based paradigm that generates each frame independently, enabling low-latency real-time spatial inference. By enforcing multi-view spatial consistency through explicit 3D anchors and implicit spatial memory, the model preserves global scene geometry while maintaining fine-grained visual details across viewpoint changes. We further introduce a progressive three-stage training pipeline that transforms a pretrained image diffusion model into a controllable frame model and finally into a real-time generator through few-step distillation. Experimental results show that InSpatio-WorldFM achieves strong multi-view consistency while supporting interactive exploration on consumer-grade GPUs, providing an efficient alternative to traditional video-based world models for real-time world simulation.

cs.CV↗