Live or Lie: Action-Aware Capsule Multiple Instance Learning for Risk Assessment in Live Streaming Platforms

Live streaming has become a cornerstone of today's internet, enabling massive real-time social interactions. However, it faces severe risks arising from sparse, coordinated malicious behaviors among multiple participants, which are often concealed within normal activities and challenging to detect timely and accurately. In this work, we provide a pioneering study on risk assessment in live streaming rooms, characterized by weak supervision where only room-level labels are available. We formulate the task as a Multiple Instance Learning (MIL) problem, treating each room as a bag and defining structured user-timeslot capsules as instances. These capsules represent subsequences of user actions within specific time windows, encapsulating localized behavioral patterns. Based on this formulation, we propose AC-MIL, an Action-aware Capsule MIL framework that models both individual behaviors and group-level coordination patterns. AC-MIL captures multi-granular semantics and behavioral cues through a serial and parallel architecture that jointly encodes temporal dynamics and cross-user dependencies. These signals are integrated for robust room-level risk prediction, while also offering interpretable evidence at the behavior segment level. Extensive experiments on large-scale industrial datasets from Douyin demonstrate that AC-MIL significantly outperforms MIL and sequential baselines, establishing new state-of-the-art performance in room-level risk assessment for live streaming. Moreover, AC-MIL provides capsule-level interpretability, enabling identification of risky behavior segments as actionable evidence for intervention. The project page is available at: https://qiaoyran.github.io/AC-MIL/.

Reasoning in a Combinatorial and Constrained World: Benchmarking LLMs on Natural-Language Combinatorial Optimization

While large language models (LLMs) have shown strong performance in math and logic reasoning, their ability to handle combinatorial optimization (CO) -- searching high-dimensional solution spaces under hard constraints -- remains underexplored. To bridge the gap, we introduce NLCO, a \textbf{N}atural \textbf{L}anguage \textbf{C}ombinatorial \textbf{O}ptimization benchmark that evaluates LLMs on end-to-end CO reasoning: given a language-described decision-making scenario, the model must output a discrete solution without writing code or calling external solvers. NLCO covers 43 CO problems and is organized using a four-layer taxonomy of variable types, constraint families, global patterns, and objective classes, enabling fine-grained evaluation. We provide solver-annotated solutions and comprehensively evaluate LLMs by feasibility, solution optimality, and reasoning efficiency. Experiments across a wide range of modern LLMs show that high-performing models achieve strong feasibility and solution quality on small instances, but both degrade as instance size grows, even if more tokens are used for reasoning. We also observe systematic effects across the taxonomy: set-based tasks are relatively easy, whereas graph-structured problems and bottleneck objectives lead to more frequent failures.

The Forecast After the Forecast: A Post-Processing Shift in Time Series

Time series forecasting has long been dominated by advances in model architecture, with recent progress driven by deep learning and hybrid statistical techniques. However, as forecasting models approach diminishing returns in accuracy, a critical yet underexplored opportunity emerges: the strategic use of post-processing. In this paper, we address the last-mile gap in time-series forecasting, which is to improve accuracy and uncertainty without retraining or modifying a deployed backbone. We propose $δ$-Adapter, a lightweight, architecture-agnostic way to boost deployed time series forecasters without retraining. $δ$-Adapter learns tiny, bounded modules at two interfaces: input nudging (soft edits to covariates) and output residual correction. We provide local descent guarantees, $O(δ)$ drift bounds, and compositional stability for combined adapters. Meanwhile, it can act as a feature selector by learning a sparse, horizon-aware mask over inputs to select important features, thereby improving interpretability. In addition, it can also be used as a distribution calibrator to measure uncertainty. Thus, we introduce a Quantile Calibrator and a Conformal Corrector that together deliver calibrated, personalized intervals with finite-sample coverage. Our experiments across diverse backbones and datasets show that $δ$-Adapter improves accuracy and calibration with negligible compute and no interface changes.

Deja Vu in Plots: Leveraging Cross-Session Evidence with Retrieval-Augmented LLMs for Live Streaming Risk Assessment

The rise of live streaming has transformed online interaction, enabling massive real-time engagement but also exposing platforms to complex risks such as scams and coordinated malicious behaviors. Detecting these risks is challenging because harmful actions often accumulate gradually and recur across seemingly unrelated streams. To address this, we propose CS-VAR (Cross-Session Evidence-Aware Retrieval-Augmented Detector) for live streaming risk assessment. In CS-VAR, a lightweight, domain-specific model performs fast session-level risk inference, guided during training by a Large Language Model (LLM) that reasons over retrieved cross-session behavioral evidence and transfers its local-to-global insights to the small model. This design enables the small model to recognize recurring patterns across streams, perform structured risk assessment, and maintain efficiency for real-time deployment. Extensive offline experiments on large-scale industrial datasets, combined with online validation, demonstrate the state-of-the-art performance of CS-VAR. Furthermore, CS-VAR provides interpretable, localized signals that effectively empower real-world moderation for live streaming.

Airy Beamforming for Radiative Near-Field MU-XL-MIMO: Overcoming Half-Space Blockage

The move to next-generation wireless communications with extremely large-scale antenna arrays (ELAAs) brings the communications into the radiative near-field (RNF) region, where distance-aware focusing is feasible. However, high-frequency RNF links are highly vulnerable to blockage in indoor environments dominated by half-space obstacles (walls, corners) that create knife-edge shadows. Conventional near-field focused beams offer high gain in line-of-sight (LoS) scenarios but suffer from severe energy truncation and effective-rank collapse in shadowed regions, often necessitating the deployment of auxiliary hardware such as Reconfigurable Intelligent Surfaces (RIS) to restore connectivity. We propose a beamforming strategy that exploits the auto-bending property of Airy beams to mitigate half-space blockage without additional hardware. The Airy beam is designed to ``ride'' the diffraction edge, accelerating its main lobe into the shadow to restore connectivity. Our contributions are threefold: (i) a Green's function-based RNF multi-user channel model that analytically reveals singular-value collapse behind knife-edge obstacles; (ii) an Airy analog beamforming scheme that optimizes the bending trajectory to recover the effective channel rank; and (iii) an Airy null-steering method that aligns oscillatory nulls with bright-region users to suppress interference in mixed shadow/bright scenarios. Simulations show that the proposed edge-riding Airy strategy achieves a Signal-to-Noise Ratio (SNR) improvement of over 20 dB and restores full-rank connectivity in shadowed links compared to conventional RNF focusing, virtually eliminating outage in geometric shadows and increasing multi-user spectral efficiency by approximately 35\% under typical indoor ELAA configurations. These results demonstrate robust RNF multi-user access in half-space blockage scenarios without relying on RIS.

MathMixup: Boosting LLM Mathematical Reasoning with Difficulty-Controllable Data Synthesis and Curriculum Learning

In mathematical reasoning tasks, the advancement of Large Language Models (LLMs) relies heavily on high-quality training data with clearly defined and well-graded difficulty levels. However, existing data synthesis methods often suffer from limited diversity and lack precise control over problem difficulty, making them insufficient for supporting efficient training paradigms such as curriculum learning. To address these challenges, we propose MathMixup, a novel data synthesis paradigm that systematically generates high-quality, difficulty-controllable mathematical reasoning problems through hybrid and decomposed strategies. Automated self-checking and manual screening are incorporated to ensure semantic clarity and a well-structured difficulty gradient in the synthesized data. Building on this, we construct the MathMixupQA dataset and design a curriculum learning strategy that leverages these graded problems, supporting flexible integration with other datasets. Experimental results show that MathMixup and its curriculum learning strategy significantly enhance the mathematical reasoning performance of LLMs. Fine-tuned Qwen2.5-7B achieves an average score of 52.6\% across seven mathematical benchmarks, surpassing previous state-of-the-art methods. These results fully validate the effectiveness and broad applicability of MathMixup in improving the mathematical reasoning abilities of LLMs and advancing data-centric curriculum learning.

Toward expert-level motivational interviewing for health behavior improvement with LLMs

Background: Motivational interviewing (MI) is an effective counseling approach for promoting health behavior change, but its impact is constrained by the need for highly trained human counselors. Objective: This study aimed to explore a scalable alternative by developing and evaluating Large Language Models for Motivational Interviewing (MI-LLMs). Methods: We first curated five Chinese psychological counseling corpora and, using GPT-4 with an MI-informed prompt, transcribed multi-turn dialogues from the two highest-quality datasets (CPsyCounD and PsyDTCorpus) into 2,040 MI-style counseling conversations, of which 2,000 were used for training and 40 for testing. Three Chinese-capable open-source LLMs (Baichuan2-7B-Chat, ChatGLM-4-9B-Chat and Llama-3-8B-Chinese-Chat-v2) were fine-tuned on this corpus and were named as MI-LLMs. We evaluated MI-LLMs using round-based automatic metrics and expert manual coding with the Motivational Interviewing Treatment Integrity (MITI) Coding Manual 4.2.1. Results: Across all three models, fine-tuning substantially improved BLEU-4 and ROUGE scores compared with the base models, and manual coding showed that MI-LLMs achieved technical and relational global scores, and MI-adherent ratios that approached those of real MI dialogues, although complex reflections and reflection-to-question ratios remained less frequent. Conclusions: These findings provide initial evidence that MI-oriented fine-tuning can endow general-purpose LLMs with core MI-consistent counseling behaviors, suggesting a scalable pathway toward AI-assisted health behavior change support while underscoring the need for further work on data scale, complex MI skills and real-world intervention trials.

DeepBooTS: Dual-Stream Residual Boosting for Drift-Resilient Time-Series Forecasting

Time-Series (TS) exhibits pronounced non-stationarity. Consequently, most forecasting methods display compromised robustness to concept drift, despite the prevalent application of instance normalization. We tackle this challenge by first analysing concept drift through a bias-variance lens and proving that weighted ensemble reduces variance without increasing bias. These insights motivate DeepBooTS, a novel end-to-end dual-stream residual-decreasing boosting method that progressively reconstructs the intrinsic signal. In our design, each block of a deep model becomes an ensemble of learners with an auxiliary output branch forming a highway to the final prediction. The block-wise outputs correct the residuals of previous blocks, leading to a learning-driven decomposition of both inputs and targets. This method enhances versatility and interpretability while substantially improving robustness to concept drift. Extensive experiments, including those on large-scale datasets, show that the proposed method outperforms existing methods by a large margin, yielding an average performance improvement of 15.8% across various datasets, establishing a new benchmark for TS forecasting.

SurveyGen-I: Consistent Scientific Survey Generation with Evolving Plans and Memory-Guided Writing

Survey papers play a critical role in scientific communication by consolidating progress across a field. Recent advances in Large Language Models (LLMs) offer a promising solution by automating key steps in the survey-generation pipeline, such as retrieval, structuring, and summarization. However, existing LLM-based approaches often struggle with maintaining coherence across long, multi-section surveys and providing comprehensive citation coverage. To address these limitations, we introduce SurveyGen-I, an automatic survey generation framework that combines coarse-to-fine retrieval, adaptive planning, and memory-guided generation. SurveyGen-I first performs survey-level retrieval to construct the initial outline and writing plan, and then dynamically refines both during generation through a memory mechanism that stores previously written content and terminology, ensuring coherence across subsections. When the system detects insufficient context, it triggers fine-grained subsection-level retrieval. During generation, SurveyGen-I leverages this memory mechanism to maintain coherence across subsections. Experiments across four scientific domains demonstrate that SurveyGen-I consistently outperforms previous works in content quality, consistency, and citation coverage.

GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

We present GLM-4.1V-Thinking, a vision-language model (VLM) designed to advance general-purpose multimodal understanding and reasoning. In this report, we share our key findings in the development of the reasoning-centric training framework. We first develop a capable vision foundation model with significant potential through large-scale pre-training, which arguably sets the upper bound for the final performance. We then propose Reinforcement Learning with Curriculum Sampling (RLCS) to unlock the full potential of the model, leading to comprehensive capability enhancement across a diverse range of tasks, including STEM problem solving, video understanding, content recognition, coding, grounding, GUI-based agents, and long document understanding. We open-source GLM-4.1V-9B-Thinking, which achieves state-of-the-art performance among models of comparable size. In a comprehensive evaluation across 28 public benchmarks, our model outperforms Qwen2.5-VL-7B on nearly all tasks and achieves comparable or even superior performance on 18 benchmarks relative to the significantly larger Qwen2.5-VL-72B. Notably, GLM-4.1V-9B-Thinking also demonstrates competitive or superior performance compared to closed-source models such as GPT-4o on challenging tasks including long document understanding and STEM reasoning, further underscoring its strong capabilities. Code, models and more information are released at https://github.com/THUDM/GLM-4.1V-Thinking.