arXiv subjects

Weiyan Shi

Publications and source records attributed to Weiyan Shi.

At least 37 records · Page 2Linked to original sources

arXiv2026

When Drawing Is Not Enough: Exploring Spontaneous Speech with Sketch for Intent Alignment in Multimodal LLMs

Early-stage design ideation often relies on rough sketches created under time pressure, leaving much of the designer's intent implicit. In practice, designers frequently speak while sketching, verbally articulating functional goals and ideas that are difficult to express visually. We introduce TalkSketchD, a sketch-while-speaking dataset that captures spontaneous speech temporally aligned with freehand sketches during early-stage toaster ideation. To examine the dataset's value, we conduct a sketch-to-image generation study comparing sketch-only inputs with sketches augmented by concurrent speech transcripts using multimodal large language models (MLLMs). Generated images are evaluated against designers' self-reported intent using a reasoning MLLM as a judge. Quantitative results show that incorporating spontaneous speech significantly improves judged intent alignment of generated design images across form, function, experience, and overall intent. These findings demonstrate that temporally aligned sketch-and-speech data can enhance MLLMs' ability to interpret user intent in early-stage design ideation.

cs.HC↗

arXiv2026

More Than 1v1: Human-AI Alignment in Early Developmental Communities with Multimodal LLMs

In early developmental contexts, particularly in parent-child interaction analysis, alignment involves families and professionals such as speech-language pathologists (SLPs) who interpret children's everyday interactions from different roles. When multimodal large language models (MLLMs) are introduced to support this process, alignment becomes a question of how authority, responsibility, and emotional risk are distributed across stakeholders. Through a three-part study with five families and three SLPs, we trace how MLLM-generated outputs move from expert-facing analysis to parent-facing feedback. We propose layered community alignment: grounding representations in expert-aligned structures, mediating translation through professional guardrails, and enabling family-level adaptation within those boundaries. We argue that alignment in developmental settings should be treated as a community-governed process rather than an individual optimisation problem.

cs.HC↗

arXiv2026

Assessing Risks of Large Language Models in Mental Health Support: A Framework for Automated Clinical AI Red Teaming

Large Language Models (LLMs) are increasingly utilized for mental health support; however, current safety benchmarks often fail to detect the complex, longitudinal risks inherent in therapeutic dialogue. We introduce an evaluation framework that pairs AI psychotherapists with simulated patient agents equipped with dynamic cognitive-affective models and assesses therapy session simulations against a comprehensive quality of care and risk ontology. We apply this framework to a high-impact test case, Alcohol Use Disorder, evaluating six AI agents (including ChatGPT, Gemini, and Character AI) against a clinically-validated cohort of 15 patient personas representing diverse clinical phenotypes. Our large-scale simulation (N=369 sessions) reveals critical safety gaps in the use of AI for mental health support. We identify specific iatrogenic risks, including the validation of patient delusions ("AI Psychosis") and failure to de-escalate suicide risk. Finally, we validate an interactive data visualization dashboard with diverse stakeholders, including AI engineers and red teamers, mental health professionals, and policy experts (N=9), demonstrating that this framework effectively enables stakeholders to audit the "black box" of AI psychotherapy. These findings underscore the critical safety risks of AI-provided mental health support and the necessity of simulation-based clinical red teaming before deployment.

cs.CL↗

arXiv2026

SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning

Recent advances in reinforcement learning have shown that language models can develop sophisticated reasoning through training on tasks with verifiable rewards, but these approaches depend on human-curated problem-answer pairs and domain-specific reward engineering. We introduce SPIRAL, a self-play framework where models learn by playing multi-turn, zero-sum games against continuously improving versions of themselves, generating an automatic curriculum of stronger opponents, and eliminating the need for human supervision. To enable this self-play training at scale, we implement a fully online, multi-turn, multi-agent reinforcement learning system for LLMs and propose role-conditioned advantage estimation (RAE) to stabilize multi-agent training. SPIRAL produces reasoning capabilities that transfer broadly, improving performance by up to 10% across a suite of 8 reasoning benchmarks on 4 different models spanning Qwen and Llama model families, outperforming supervised fine-tuning on 25,000 expert game trajectories. Multi-game training (TicTacToe, Kuhn Poker, Simple Negotiation) yields the strongest results, with improvements observed across both base and instruction-tuned models. Analysis of chain-of-thought traces reveals that games develop distinct cognitive patterns that transfer to improve reasoning performance, with different games developing complementary strengths. Even models which have already been trained on reasoning tasks using RLVR, like DeepSeek-R1-Distill-Qwen-7B, still benefit from our approach. These results demonstrate that zero-sum games naturally develop transferable reasoning capabilities across diverse model architectures and training stages, highlighting a promising direction for autonomous reasoning development. Our code can be found in https://github.com/spiral-rl/spiral.

cs.AI↗

arXiv2026

PolySkill: Learning Generalizable Skills Through Polymorphic Abstraction

Large language models (LLMs) are moving beyond static uses and are now powering agents that learn continually during their interaction with external environments. For example, agents can learn reusable skills while navigating web pages or toggling new tools. However, existing methods for skill learning often create skills that are over-specialized to a single website and fail to generalize. We introduce PolySkill, a new framework that enables agents to learn generalizable and compositional skills. The core idea, inspired by polymorphism in software engineering, is to decouple a skill's abstract goal (what it accomplishes) and its concrete implementation (how it is executed). Experiments show that our method (1) improves skill reuse by 1.7x on seen websites and (2) boosts success rates by up to 9.4% on Mind2Web and 13.9% on unseen websites, while reducing steps by over 20%. (3) In self-exploration settings without specified tasks, our framework improves the quality of proposed tasks and enables agents to learn generalizable skills that work across different sites. By enabling the agent to identify and refine its own goals, the PolySkill enhances the agent's ability to learn a better curriculum, leading to the acquisition of more generalizable skills compared to baseline methods. This work provides a practical path toward building agents capable of continual learning in adaptive environments. Our findings show that separating a skill's goal from its execution is a crucial step toward developing autonomous agents that can learn and generalize across the open web continuously. Our code can be found in https://github.com/simonucl/PolySkill.

cs.CL↗

arXiv2026

Towards Aligning Multimodal LLMs with Human Experts: A Focus on Parent-Child Interaction

While multimodal large language models (MLLMs) are increasingly applied in human-centred AI systems, their ability to understand complex social interactions remains uncertain. We present an exploratory study on aligning MLLMs with speech-language pathologists (SLPs) in analysing joint attention in parent-child interactions, a key construct in early social-communicative development. Drawing on interviews and video annotations with three SLPs, we characterise how observational cues of gaze, action, and vocalisation inform their reasoning processes. We then test whether an MLLM can approximate this workflow through a two-stage prompting approach, separating observation from judgement. Our findings reveal that alignment is more robust at the observation layer, where experts share common descriptors, than at the judgement layer, where interpretive criteria diverge. We position this work as a case-based probe into expert-AI alignment in complex social behaviour, highlighting both the feasibility and the challenges of applying MLLMs to socially situated interaction analysis.

cs.HC↗

arXiv2026

GEM: A Gym for Agentic LLMs

The training paradigm for large language models (LLMs) is moving from static datasets to experience-based learning, where agents acquire skills via interacting with complex environments. To facilitate this transition we introduce GEM (General Experience Maker), an open-source environment simulator designed for the age of LLMs. Analogous to OpenAI-Gym for traditional reinforcement learning (RL), GEM provides a standardized framework for the environment-agent interface, including asynchronous vectorized execution for high throughput, and flexible wrappers for easy extensibility. GEM also features a diverse suite of environments, robust integrated tools, and single-file example scripts demonstrating using GEM with five popular RL training frameworks. Along with this, we also provide a set of baselines across 24 environments using REINFORCE with Return Batch Normalization (ReBN), which -- unlike GRPO -- is compatible with the full RL setting of dense per-turn rewards and offers better credit assignment. We further conduct apple-to-apple benchmarking of PPO, GRPO and REINFORCE in both single- and multi-turn settings using GEM to shed light on the algorithmic designs. Lastly, GEM also functions as a convenient evaluation toolkit besides a training environment. We hope this framework can help accelerate future agentic LLM research.

cs.LG↗

arXiv2026

A Taxonomy of Human--MLLM Interaction in Early-Stage Sketch-Based Design Ideation

As multimodal large language models (MLLMs) are increasingly integrated into early-stage design tools, it is important to understand how designers collaborate with AI during ideation. In a user study with 12 participants, we analysed sketch-based design interactions with an MLLM-powered system using automatically recorded interaction logs and post-task interviews. Based on how creative responsibility was allocated between humans and the AI, we predefined four interaction modes: Human-Only, Human-Lead, AI-Lead, and Co-Evolution, and analysed how these modes manifested during sketch-based design ideation. Our results show that designers rarely rely on a single mode; instead, human-led and AI-led roles are frequently interwoven and shift across ideation instances. These findings provide an empirical basis for future work to investigate why designers shift roles with AI and how interactive systems can better support such dynamic collaboration.

cs.HC↗

arXiv2026

NewsInterview: a Dataset and a Playground to Evaluate LLMs' Ground Gap via Informational Interviews

Large Language Models (LLMs) have demonstrated impressive capabilities in generating coherent text but often struggle with grounding language and strategic dialogue. To address this gap, we focus on journalistic interviews, a domain rich in grounding communication and abundant in data. We curate a dataset of 40,000 two-person informational interviews from NPR and CNN, and reveal that LLMs are significantly less likely than human interviewers to use acknowledgements and to pivot to higher-level questions. Realizing that a fundamental deficit exists in multi-turn planning and strategic thinking, we develop a realistic simulated environment, incorporating source personas and persuasive elements, in order to facilitate the development of agents with longer-horizon rewards. Our experiments show that while source LLMs mimic human behavior in information sharing, interviewer LLMs struggle with recognizing when questions are answered and engaging persuasively, leading to suboptimal information extraction across model size and capability. These findings underscore the need for enhancing LLMs' strategic dialogue capabilities.

cs.CL↗

arXiv2026

Open-Source Multimodal Moxin Models with Moxin-VLM and Moxin-VLA

Recently, Large Language Models (LLMs) have undergone a significant transformation, marked by a rapid rise in both their popularity and capabilities. Leading this evolution are proprietary LLMs like GPT-4 and GPT-o1, which have captured widespread attention in the AI community due to their remarkable performance and versatility. Simultaneously, open-source LLMs, such as LLaMA and Mistral, have made great contributions to the ever-increasing popularity of LLMs due to the ease to customize and deploy the models across diverse applications. Moxin 7B is introduced as a fully open-source LLM developed in accordance with the Model Openness Framework, which moves beyond the simple sharing of model weights to embrace complete transparency in training, datasets, and implementation detail, thus fostering a more inclusive and collaborative research environment that can sustain a healthy open-source ecosystem. To further equip Moxin with various capabilities in different tasks, we develop three variants based on Moxin, including Moxin-VLM, Moxin-VLA, and Moxin-Chinese, which target the vision-language, vision-language-action, and Chinese capabilities, respectively. Experiments show that our models achieve superior performance in various evaluations. We adopt open-source framework and open data for the training. We release our models, along with the available data and code to derive these models.

cs.CL↗

arXiv2026

SocialFusion: Addressing Social Degradation in Pre-trained Vision-Language Models

Understanding social interactions from visual cues is a fundamental challenge for a socially competent AI. While powerful pre-trained vision-language models (VLMs) have shown remarkable general capabilities, they surprisingly struggle to unify and learn multiple social perception tasks simultaneously, often exhibiting negative transfer. We identify that this negative transfer stems from a critical issue we term "social degradation," whereby the general visual-linguistic pre-training process of VLMs impairs the visual encoder's ability to represent nuanced social information. We investigate this behavior further under two lenses: decodability through linear representation probing and compatibility through gradient conflict analysis, revealing that both play a role in the degradation, especially the former, which is significantly compromised in the VLM pre-training process. To address these issues, we propose SocialFusion, a unified framework that learns a minimal connection between a frozen visual encoder and a language model. Compared with existing VLMs, it exhibits positive transfer across all five social tasks, leveraging synergies between them to enhance overall performance and achieves comparable performance to task-specific state-of-the-art models on various benchmarks. Our findings suggest that current VLM pre-training strategies may be detrimental to acquiring general social competence and highlight the need for more socially-aware training paradigms.

cs.CV↗

arXiv2026

Human-AI Alignment of Multimodal Large Language Models with Speech-Language Pathologists in Parent-Child Interactions

Joint attention is a critical marker of early social-communicative development, yet remains difficult for caregivers to assess without expert guidance. In this work, we explore how multimodal large language models (MLLMs) can be aligned with the reasoning processes of speech-language pathologists (SLPs) to support the interpretation of everyday parent-child interactions. We conducted in-depth interviews and video annotation studies with three experienced SLPs to uncover how they evaluate joint attention based on three core behavioural cues: gaze, action, and vocalisation. Using these insights, we developed a two-stage MLLM-based system that first extracts fine-grained behavioural descriptions from video segments and then judge joint attention quality using expert-aligned prompts. Our evaluation across 26 parent-child interaction videos shows that MLLMs can achieve up to 85% accuracy in perceptual cue extraction and over 75% average precision in simulating expert judgement. We further propose design guidelines for building MLLM-based behaviour observation-judgement systems that align with SLPs, emphasising the structuring of behavioural cues, the construction of exemplar libraries grounded in expert annotations, and the need to personalise system responses based on developmental stage and neurotypical or atypical presentation. This work provides structured behavioural cues derived from SLP expertise, demonstrates the feasibility of aligning SLPs observation and judgement using MLLMs, and offers practical design guidelines for building aligned systems to support parent-child interaction analysis.

cs.HC↗

arXiv2025

TalkSketch: Multimodal Generative AI for Real-time Sketch Ideation with Speech

Sketching is a widely used medium for generating and exploring early-stage design concepts. While generative AI (GenAI) chatbots are increasingly used for idea generation, designers often struggle to craft effective prompts and find it difficult to express evolving visual concepts through text alone. In the formative study (N=6), we examined how designers use GenAI during ideation, revealing that text-based prompting disrupts creative flow. To address these issues, we developed TalkSketch, an embedded multimodal AI sketching system that integrates freehand drawing with real-time speech input. TalkSketch aims to support a more fluid ideation process through capturing verbal descriptions during sketching and generating context-aware AI responses. Our work highlights the potential of GenAI tools to engage the design process itself rather than focusing on output.

cs.HC↗

arXiv2025

7B Fully Open Source Moxin-LLM/VLM -- From Pretraining to GRPO-based Reinforcement Learning Enhancement

Recently, Large Language Models (LLMs) have undergone a significant transformation, marked by a rapid rise in both their popularity and capabilities. Leading this evolution are proprietary LLMs like GPT-4 and GPT-o1, which have captured widespread attention in the AI community due to their remarkable performance and versatility. Simultaneously, open-source LLMs, such as LLaMA, have made great contributions to the ever-increasing popularity of LLMs due to the ease to customize and deploy the models across diverse applications. Although open-source LLMs present unprecedented opportunities for innovation and research, the commercialization of LLMs has raised concerns about transparency, reproducibility, and safety. Many open-source LLMs fail to meet fundamental transparency requirements by withholding essential components like training code and data, which may hinder further innovations on LLMs. To mitigate this issue, we introduce Moxin 7B, a fully open-source LLM developed, adhering to principles of open science, open source, open data, and open access. We release the pre-training code and configurations, training and fine-tuning datasets, and intermediate and final checkpoints, aiming to make continuous commitments to fully open-source LLMs. After pre-training the base model, we finetune the Moxin Base model with SOTA post-training framework and instruction data to obtain Moxin Instruct model. To improve the reasoning capability, we further finetune our Instruct model with chain-of-thought data distilled from DeepSeek R1, and then use Group Relative Policy Optimization (GRPO) following DeepSeek R1 to finetune our model, leading to the Moxin Reasoning model. Moreover, we develop our vision language model based on our Moxin model. Experiments show that our models achieve superior performance in various evaluations such as zero-shot evaluation, few-shot evaluation, and CoT evaluation.

cs.CL↗

arXiv2025

Sword and Shield: Uses and Strategies of LLMs in Navigating Disinformation

The emergence of Large Language Models (LLMs) presents a dual challenge in the fight against disinformation. These powerful tools, capable of generating human-like text at scale, can be weaponised to produce sophisticated and persuasive disinformation, yet they also hold promise for enhancing detection and mitigation strategies. This paper investigates the complex dynamics between LLMs and disinformation through a communication game that simulates online forums, inspired by the game Werewolf, with 25 participants. We analyse how Disinformers, Moderators, and Users leverage LLMs to advance their goals, revealing both the potential for misuse and combating disinformation. Our findings highlight the varying uses of LLMs depending on the participants' roles and strategies, underscoring the importance of understanding their effectiveness in this context. We conclude by discussing implications for future LLM development and online platform design, advocating for a balanced approach that empowers users and fosters trust while mitigating the risks of LLM-assisted disinformation.

cs.HC↗

arXiv2025

WiCross: Indoor Human Zone-Crossing Detection Using Commodity WiFi Devices

Detecting whether a target crosses the given zone (e.g., a door) can enable various practical applications in smart homes, including intelligent security and people counting. The traditional infrared-based approach only covers a line and can be easily cracked. In contrast, reusing the ubiquitous WiFi devices deployed in homes has the potential to cover a larger area of interest as WiFi signals are scattered throughout the entire space. By detecting the walking direction (i.e., approaching and moving away) with WiFi signal strength change, existing work can identify the behavior of crossing between WiFi transceiver pair. However, this method mistakenly classifies the turn-back behavior as crossing behavior, resulting in a high false alarm rate. In this paper, we propose WiCross, which can accurately distinguish the turn-back behavior with the phase statistics pattern of WiFi signals and thus robustly identify whether the target crosses the area between the WiFi transceiver pair. We implement WiCross with commercial WiFi devices and extensive experiments demonstrate that WiCross can achieve an accuracy higher than 95\% with a false alarm rate of less than 5%.

cs.HC↗

arXiv2025

Towards Multimodal Large-Language Models for Parent-Child Interaction: A Focus on Joint Attention

Joint attention is a critical component of early speech-language development and a key indicator of effective parent-child interaction. However, research on detecting and analysing joint attention remains limited, particularly for Multimodal Large Language Models (MLLMs). This study evaluates MLLMs' ability to comprehend joint attention by analysing 26 parent-child interaction videos annotated by two speech-language pathologists. These annotations identify strong and poor joint attention segments, serving as benchmarks for evaluating the models' interpretive capabilities. Our findings reveal that current MLLMs struggle to accurately interpret joint attention due to a lack of nuanced understanding of child-initiated eye contact, a crucial component of joint attention dynamics. This study highlights the importance of incorporating detailed eye contact to enhance MLLMs' multimodal reasoning. Addressing these gaps is essential for future research to advance the use of MLLMs in analysing and supporting parent-child interactions.

cs.HC↗

arXiv2025

Labeling Messages as AI-Generated Does Not Reduce Their Persuasive Effects

As generative artificial intelligence (AI) enables the creation and dissemination of information at massive scale and speed, it is increasingly important to understand how people perceive AI-generated content. One prominent policy proposal requires explicitly labeling AI-generated content to increase transparency and encourage critical thinking about the information, but prior research has not yet tested the effects of such labels. To address this gap, we conducted a survey experiment (N=1601) on a diverse sample of Americans, presenting participants with an AI-generated message about several public policies (e.g., allowing colleges to pay student-athletes), randomly assigning whether participants were told the message was generated by (a) an expert AI model, (b) a human policy expert, or (c) no label. We found that messages were generally persuasive, influencing participants' views of the policies by 9.74 percentage points on average. However, while 94.6% of participants assigned to the AI and human label conditions believed the authorship labels, labels had no significant effects on participants' attitude change toward the policies, judgments of message accuracy, nor intentions to share the message with others. These patterns were robust across a variety of participant characteristics, including prior knowledge of the policy, prior experience with AI, political party, education level, or age. Taken together, these results imply that, while authorship labels would likely enhance transparency, they are unlikely to substantially affect the persuasiveness of the labeled content, highlighting the need for alternative strategies to address challenges posed by AI-generated information.

cs.CY↗