arXiv subjects

Yu Wang

Publications and source records attributed to Yu Wang.

At least 325 records · Page 18Linked to original sources

arXiv2026

Exposing Cross-Modal Consistency for Fake News Detection in Short-Form Videos

Short-form video platforms are major channels for news but also fertile ground for multimodal misinformation where each modality appears plausible alone yet cross-modal relationships are subtly inconsistent, like mismatched visuals and captions. On two benchmark datasets, FakeSV (Chinese) and FakeTT (English), we observe a clear asymmetry: real videos exhibit high text-visual but moderate text-audio consistency, while fake videos show the opposite pattern. Moreover, a single global consistency score forms an interpretable axis along which fake probability and prediction errors vary smoothly. Motivated by these observations, we present MAGIC3 (Modal-Adversarial Gated Interaction and Consistency-Centric Classifier), a detector that explicitly models and exposes cross-tri-modal consistency signals at multiple granularities. MAGIC3 combines explicit pairwise and global consistency modeling with token- and frame-level consistency signals derived from cross-modal attention, incorporates multi-style LLM rewrites to obtain style-robust text representations, and employs an uncertainty-aware classifier for selective VLM routing. Using pre-extracted features, MAGIC3 consistently outperforms the strongest non-VLM baselines on FakeSV and FakeTT. While matching VLM-level accuracy, the two-stage system achieves 18-27x higher throughput and 93% VRAM savings, offering a strong cost-performance tradeoff.

cs.AI↗

arXiv2026

R3-REC: Reasoning-Driven Recommendation via Retrieval-Augmented LLMs over Multi-Granular Interest Signals

This paper addresses two persistent challenges in sequential recommendation: (i) evidence insufficiency-cold-start sparsity together with noisy, length-varying item texts; and (ii) opaque modeling of dynamic, multi-faceted intents across long/short horizons. We propose R3-REC (Reasoning-Retrieval-Recommendation), a prompt-centric, retrieval-augmented framework that unifies Multi-level User Intent Reasoning, Item Semantic Extraction, Long-Short Interest Polarity Mining, Similar User Collaborative Enhancement, and Reasoning-based Interest Matching and Scoring. Across ML-1M, Games, and Bundle, R3-REC consistently surpasses strong neural and LLM baselines, yielding improvements up to +10.2% (HR@1) and +6.4% (HR@5) with manageable end-to-end latency. Ablations corroborate complementary gains of all modules.

cs.IR↗

arXiv2026

WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning

Recent advancements in Large Language Models (LLMs) have largely focused on depth scaling, where a single agent solves long-horizon problems with multi-turn reasoning and tool use. However, as tasks grow broader, the key bottleneck shifts from individual competence to organizational capability. In this work, we explore a complementary dimension of width scaling with multi-agent systems to address broad information seeking. Existing multi-agent systems often rely on hand-crafted workflows and turn-taking interactions that fail to parallelize work effectively. To bridge this gap, we propose WideSeek-R1, a lead-agent-subagent framework trained via multi-agent reinforcement learning (MARL) to synergize scalable orchestration and parallel execution. By utilizing a shared LLM with isolated contexts and specialized tools, WideSeek-R1 jointly optimizes the lead agent and parallel subagents on a curated dataset of 20k broad information-seeking tasks. Extensive experiments show that WideSeek-R1-4B achieves an item F1 score of 40.0% on the WideSearch benchmark, which is comparable to the performance of single-agent DeepSeek-R1-671B. Furthermore, WideSeek-R1-4B exhibits consistent performance gains as the number of parallel subagents increases, highlighting the effectiveness of width scaling.

cs.AI↗

arXiv2026

Robust Joint Modeling for Data with Continuous and Binary Responses

In many supervised learning applications, the response consists of both continuous and binary outcomes. Studies have shown that jointly modeling such mixed-type responses can substantially improve predictive performance compared to separate analyses. But outliers pose a new challenge to the existing likelihood-based modeling approaches. In this paper, we propose a new robust joint modeling framework for data with both continuous and binary responses. It is based on the density power divergence (DPD) loss function with the $\ell_1$ regularization. The proposed framework leads to a sparse estimator that simultaneously predicts continuous and binary responses in high-dimensional input settings while down-weighting influential outliers and mislabeled samples. We also develop an efficient proximal gradient algorithm with Barzilai-Borwein spectral step size and a robust information criterion (RIC) for data-driven selection of the penalty parameters. Extensive simulation studies under a variety of contamination schemes demonstrate that the proposed method achieves lower prediction error and more accurate parameter estimation than several competing approaches. A real case study on wafer lapping in semiconductor manufacturing further illustrates the practical gains in predictive accuracy, robustness, and interpretability of the proposed framework.

stat.ME↗

arXiv2026

Islands of Electromagnetic Tranquility in Our Galactic core and Little Red Dots that Shelter Molecules and Prebiotic Chemistry

Both the Galactic Center and little red dots (LRDs) host million-solar-mass black holes within dense, cold reservoirs of molecules associated with dust grains, and are electromagnetically tranquil. These conditions enable complex molecular chemistry and may serve as natural laboratories for prebiotic genetic evolution by allowing the synthesis of organic molecules essential for life.

astro-ph.GA↗

arXiv2026

Senna-2: Aligning VLM and End-to-End Driving Policy for Consistent Decision Making and Planning

Vision-language models (VLMs) enhance the planning capability of end-to-end (E2E) driving policy by leveraging high-level semantic reasoning. However, existing approaches often overlook the dual-system consistency between VLM's high-level decision and E2E's low-level planning. As a result, the generated trajectories may misalign with the intended driving decisions, leading to weakened top-down guidance and decision-following ability of the system. To address this issue, we propose Senna-2, an advanced VLM-E2E driving policy that explicitly aligns the two systems for consistent decision-making and planning. Our method follows a consistency-oriented three-stage training paradigm. In the first stage, we conduct driving pre-training to achieve preliminary decision-making and planning, with a decision adapter transmitting VLM decisions to E2E policy in the form of implicit embeddings. In the second stage, we align the VLM and the E2E policy in an open-loop setting. In the third stage, we perform closed-loop alignment via bottom-up Hierarchical Reinforcement Learning in 3DGS environments to reinforce the safety and efficiency. Extensive experiments demonstrate that Senna-2 achieves superior dual-system consistency (19.3% F1 score improvement) and significantly enhances driving safety in both open-loop (5.7% FDE reduction) and closed-loop settings (30.6% AF-CR reduction).

cs.CV↗

arXiv2026

Gromov--Witten theory beyond maximal contacts

Given a smooth projective variety $X$ and a smooth nef divisor $D$, we identify genus zero relative Gromov--Witten invariants of $(X,D)$ with $(n+1)$ relative markings with genus zero orbifold Gromov--Witten invariants of multi-root stacks over the $\mathbb P^1$-bundle $P:=\mathbb P(\mathcal O_X(-D)\oplus \mathcal O_X)$ with $n$ orbifold markings. This is a generalization of the local-relative correspondence beyond maximal contacts. Repeating this process, we identify genus zero relative Gromov--Witten invariants of ambient insertions with genus zero absolute Gromov--Witten invariants of toric bundles. We also present how this correspondence can be used to compute genus zero two-point relative Gromov--Witten invariants.

math.AG↗

arXiv2026

Relativistic $^{56}\text{Ni}$ Decay Lines in GRB 221009A

Long Gamma Ray Bursts are thought to originate from the core collapse of massive stars that give rise to energetic broad-lined Type Ic supernovae. The brightest burst ever recorded, GRB 221009A, has been linked to a broad-lined Type Ic supernova through late-time observations by the James Webb Space Telescope. An emission line evolving from $\sim$37 to $\sim$6~MeV is detected during the prompt phase. We propose that this time-evolving line is consistent with Doppler-boosted radioactive decay of nickel synthesized in the associated supernova and entrained in the relativistic jet, corresponding to the boosted 158~keV decay branch. We also report evidence for an additional higher-energy excess near $\sim$24~MeV at 290--300~s, detected at moderate statistical significance and consistent with the boosted 270~keV decay branch. The observed kinematics and flux evolution are compatible with expectations from radioactive decay, providing direct spectroscopic evidence linking prompt emission to supernova nucleosynthesis.

astro-ph.HE↗

arXiv2026

RM-R1: Reward Modeling as Reasoning

Reward modeling is essential for aligning large language models with human preferences through reinforcement learning. To provide accurate reward signals, a reward model (RM) should stimulate deep thinking and conduct interpretable reasoning before assigning a score or a judgment. Inspired by recent advances of long chain-of-thought on reasoning-intensive tasks, we hypothesize and validate that integrating reasoning into reward modeling significantly enhances RM's interpretability and performance. We introduce a new class of generative reward models, Reasoning Reward Models (ReasRMs), which formulate reward modeling as a reasoning task. We propose a reasoning-oriented training pipeline and train a family of ReasRMs, RM-R1. RM-R1 features a chain-of-rubrics (CoR) mechanism -- self-generating sample-level chat rubrics or math/code solutions, and evaluating candidate responses against them. The training of RM-R1 consists of two key stages: (1) distillation of high-quality reasoning chains and (2) reinforcement learning with verifiable rewards. Empirically, our models achieve superior performance across three reward model benchmarks on average, outperforming much larger open-weight models (e.g., INF-ORM-Llama3.1-70B) and proprietary ones (e.g., GPT-4o) by up to 4.9%. Beyond final performance, we perform thorough analyses to understand the key ingredients of successful ReasRM training.

cs.CL↗

arXiv2026

Unify the Views: View-Consistent Prototype Learning for Few-Shot Segmentation

Few-shot segmentation (FSS) has gained significant attention for its ability to generalize to novel classes with limited supervision, yet remains challenged by structural misalignment and cross-view inconsistency under large appearance or viewpoint variations. This paper tackles these challenges by introducing VINE (View-Informed NEtwork), a unified framework that jointly models structural consistency and foreground discrimination to refine class-specific prototypes. Specifically, VINE introduces a spatial-view graph on backbone features, where the spatial graph captures local geometric topology and the view graph connects features from different perspectives to propagate view-invariant structural semantics. To further alleviate foreground ambiguity, we derive a discriminative prior from the support-query feature discrepancy to capture category-specific contrast, which reweights SAM features by emphasizing salient regions and recalibrates backbone activations for improved structural focus. The foreground-enhanced SAM features and structurally enriched ResNet features are progressively integrated through masked cross-attention, yielding class-consistent prototypes used as adaptive prompts for the SAM decoder to generate accurate masks. Extensive experiments on multiple FSS benchmarks validate the effectiveness and robustness of VINE, particularly under challenging scenarios with viewpoint shifts and complex structures. The code is available at https://github.com/HongliLiu1/VINE-main.

cs.CV↗

arXiv2026

MLLMRec-R1: Incentivizing Reasoning Capability in Large Language Models for Multimodal Sequential Recommendation

Group relative policy optimization (GRPO) has become a standard post-training paradigm for improving reasoning and preference alignment in large language models (LLMs), and has recently shown strong effectiveness in LLM-based recommender systems. However, extending GRPO-based reasoning pipelines to multimodal sequential recommendation (MSR) with multimodal large language models (MLLMs) faces fundamental obstacles. First, MSR requires jointly encoding visual content for both historical interactions and multiple candidate items, causing visual tokens to dominate the input and making the cost of group-based rollout scale with history length and candidate set size, which renders GRPO-based training prohibitively expensive. Second, existing Chain-of-Thought (CoT) supervision suffers from reward inflation in recommendation scenarios, where higher training rewards do not reliably translate into improved ranking performance and may induce shortcut learning. To address these challenges, we propose MLLMRec-R1, an efficient and stable GRPO-based reasoning framework for multimodal sequential recommendation. MLLMRec-R1 textualizes visual signals offline to eliminate expensive visual tokens while preserving multimodal semantics, and constructs high-quality multimodal CoT supervision through refinement and confidence-aware assessment. Furthermore, a mixed-grained data augmentation strategy selectively injects reliable CoT samples while retaining standard training data, mitigating reward inflation and improving generalization stability. Extensive experiments on three benchmark datasets demonstrate that MLLMRec-R1 consistently outperforms state-of-the-art methods, establishing a practical and effective GRPO-based reasoning pipeline for multimodal sequential recommendation. The code is available at https://github.com/wangyu0627/MLLMRec-R1.

cs.IR↗

arXiv2026

RAG vs. GraphRAG: A Systematic Evaluation and Key Insights

Retrieval-Augmented Generation (RAG) improves large language models (LLMs) by retrieving relevant information from external sources and has been widely adopted for text-based tasks. For structured data, such as knowledge graphs, Graph Retrieval-Augmented Generation (GraphRAG) retrieves and aggregates information along graph structures. More recently, GraphRAG has been extended to general text settings by organizing unstructured text into graph representations, showing promise for reasoning and grounding. Despite these advances, existing GraphRAG systems for text data are often tailored to specific tasks, datasets, and system designs, resulting in heterogeneous evaluation protocols. Consequently, a systematic understanding of the relative strengths, limitations, and trade-offs between RAG and GraphRAG on widely used text benchmarks remains limited. In this paper, we present a comprehensive benchmark study comparing RAG and GraphRAG on established text-based tasks, including question answering and query-based summarization. We introduce a unified evaluation protocol that standardizes data preprocessing, retrieval configurations, and generation settings, enabling fair and reproducible comparisons. Our results highlight the distinct strengths of RAG and GraphRAG across different tasks and evaluation perspectives. Building on these findings, we explore selection and integration strategies that combine the strengths of both paradigms, leading to consistent performance improvements. We further analyze failure modes, efficiency trade-offs, and evaluation biases, and highlight key considerations for designing and evaluating retrieval-augmented generation systems.

cs.IR↗

arXiv2026

InfinityStory: Unlimited Video Generation with World Consistency and Character-Aware Shot Transitions

Generating long-form storytelling videos with consistent visual narratives remains a significant challenge in video synthesis. We present a novel framework, dataset, and a model that address three critical limitations: background consistency across shots, seamless multi-subject shot-to-shot transitions, and scalability to hour-long narratives. Our approach introduces a background-consistent generation pipeline that maintains visual coherence across scenes while preserving character identity and spatial relationships. We further propose a transition-aware video synthesis module that generates smooth shot transitions for complex scenarios involving multiple subjects entering or exiting frames, going beyond the single-subject limitations of prior work. To support this, we contribute with a synthetic dataset of 10,000 multi-subject transition sequences covering underrepresented dynamic scene compositions. On VBench, InfinityStory achieves the highest Background Consistency (88.94), highest Subject Consistency (82.11), and the best overall average rank (2.80), showing improved stability, smoother transitions, and better temporal coherence.

cs.CV↗

arXiv2026

MAGE: Meta-Reinforcement Learning for Language Agents toward Strategic Exploration and Exploitation

Large Language Model (LLM) agents have demonstrated remarkable proficiency in learned tasks, yet they often struggle to adapt to non-stationary environments with feedback. While In-Context Learning and external memory offer some flexibility, they fail to internalize the adaptive ability required for long-term improvement. Meta-Reinforcement Learning (meta-RL) provides an alternative by embedding the learning process directly within the model. However, existing meta-RL approaches for LLMs focus primarily on exploration in single-agent settings, neglecting the strategic exploitation necessary for multi-agent environments. We propose MAGE, a meta-RL framework that empowers LLM agents for strategic exploration and exploitation. MAGE utilizes a multi-episode training regime where interaction histories and reflections are integrated into the context window. By using the final episode reward as the objective, MAGE incentivizes the agent to refine its strategy based on past experiences. We further combine population-based training with an agent-specific advantage normalization technique to enrich agent diversity and ensure stable learning. Experiment results show that MAGE outperforms existing baselines in both exploration and exploitation tasks. Furthermore, MAGE exhibits strong generalization to unseen opponents, suggesting it has internalized the ability for strategic exploration and exploitation. Code is available at https://github.com/Lu-Yang666/MAGE.

cs.AI↗

arXiv2026

Adaptive Location Hierarchy Learning for Long-Tailed Mobility Prediction

Human mobility prediction is crucial for applications ranging from location-based recommendations to urban planning, which aims to forecast users' next location visits based on historical trajectories. While existing mobility prediction models excel at capturing sequential patterns through diverse architectures for different scenarios, they are hindered by the long-tailed distribution of location visits, leading to biased predictions and limited applicability. This highlights the need for a solution that enhances the long-tailed prediction capabilities of these models with broad compatibility and efficiency across diverse architectures. To address this need, we propose the first architecture-agnostic plugin for long-tailed human mobility prediction, named \textbf{A}daptive \textbf{LO}cation \textbf{H}ier\textbf{A}rchy learning (ALOHA). Inspired by Maslow's theory of human motivation, we exploit and explore common mobility knowledge of head and tail locations derived from human mobility trajectories to effectively mitigate long-tailed bias. Specifically, we introduce an automatic pipeline to construct city-tailored location hierarchies based on Large Language Models (LLMs) and Chain-of-Thought (CoT) prompts, capturing high-level mobility semantics with minimal human verification. We further design an Adaptive Hierarchical Loss (AHL) that rebalances learning through Gumbel disturbance and node-wise adaptive weighting, enabling both exploitation of multi-level signals and exploration within semantically related groups. Extensive experiments across multiple state-of-the-art models demonstrate that ALOHA consistently improves long-tailed mobility prediction performance by up to 16.59\% while maintaining efficiency and robustness. Our code is at https://github.com/Star607/ALOHA.

cs.AI↗

arXiv2026

Cache-to-Cache: Direct Semantic Communication Between Large Language Models

Multi-LLM systems harness the complementary strengths of diverse Large Language Models, achieving performance and efficiency gains that are not attainable by a single model. In existing designs, LLMs communicate through text, forcing internal representations to be transformed into output token sequences. This process both loses rich semantic information and incurs token-by-token generation latency. Motivated by these limitations, we ask: Can LLMs communicate beyond text? Oracle experiments show that enriching the KV-Cache semantics can improve response quality without increasing cache size, supporting KV-Cache as an effective medium for inter-model communication. Thus, we propose Cache-to-Cache (C2C), a new paradigm for direct semantic communication between LLMs. C2C uses a neural network to project and fuse the source model's KV-cache with that of the target model to enable direct semantic transfer. A learnable gating mechanism selects the target layers that benefit from cache communication. Compared with text communication, C2C utilizes the deep, specialized semantics from both models, while avoiding explicit intermediate text generation. Experiments show that C2C achieves 6.4-14.2% higher average accuracy than individual models. It further outperforms the text communication paradigm by approximately 3.1-5.4%, while delivering an average 2.5x speedup in latency. Our code is available at https://github.com/thu-nics/C2C.

cs.CL↗

arXiv2026

CLEAR: Null-Space Projection for Cross-Modal De-Redundancy in Multimodal Recommendation

Multimodal recommendation has emerged as an effective paradigm for enhancing collaborative filtering by incorporating heterogeneous content modalities. Existing multimodal recommenders predominantly focus on reinforcing cross-modal consistency to facilitate multimodal fusion. However, we observe that multimodal representations often exhibit substantial cross-modal redundancy, where dominant shared components overlap across modalities. Such redundancy can limit the effective utilization of complementary information, explaining why incorporating additional modalities does not always yield performance improvements. In this work, we propose CLEAR, a lightweight and plug-and-play cross-modal de-redundancy approach for multimodal recommendation. Rather than enforcing stronger cross-modal alignment, CLEAR explicitly characterizes the redundant shared subspace across modalities by modeling cross-modal covariance between visual and textual representations. By identifying dominant shared directions via singular value decomposition and projecting multimodal features onto the complementary null space, CLEAR reshapes the multimodal representation space by suppressing redundant cross-modal components while preserving modality-specific information. This subspace-level projection implicitly regulates representation learning dynamics, preventing the model from repeatedly amplifying redundant shared semantics during training. Notably, CLEAR can be seamlessly integrated into existing multimodal recommenders without modifying their architectures or training objectives. Extensive experiments on three public benchmark datasets demonstrate that explicitly reducing cross-modal redundancy consistently improves recommendation performance across a wide range of multimodal recommendation models.

cs.IR↗

arXiv2026

Weakly Supervised Video Anomaly Detection with Anomaly-Connected Components and Intention Reasoning

Weakly supervised video anomaly detection (WS-VAD) involves identifying the temporal intervals that contain anomalous events in untrimmed videos, where only video-level annotations are provided as supervisory signals. However, a key limitation persists in WS-VAD, as dense frame-level annotations are absent, which often leaves existing methods struggling to learn anomaly semantics effectively. To address this issue, we propose a novel framework named LAS-VAD, short for Learning Anomaly Semantics for WS-VAD, which integrates anomaly-connected component mechanism and intention awareness mechanism. The former is designed to assign video frames into distinct semantic groups within a video, and frame segments within the same group are deemed to share identical semantic information. The latter leverages an intention-aware strategy to distinguish between similar normal and abnormal behaviors (e.g., taking items and stealing). To further model the semantic information of anomalies, as anomaly occurrence is accompanied by distinct characteristic attributes (i.e., explosions are characterized by flames and thick smoke), we additionally incorporate anomaly attribute information to guide accurate detection. Extensive experiments on two benchmark datasets, XD-Violence and UCF-Crime, demonstrate that our LAS-VAD outperforms current state-of-the-art methods with remarkable gains.

cs.CV↗