Current approaches for Multimodal Sentiment Analysis (MSA) primarily leverage the knowledge and reasoning capabilities of parameter-heavy (Multimodal) LLMs for classification, overlooking autonomous multimodal sentiment reasoning generation in resource-constrained environments. In this paper, we focus on the Resource-L...
Haonan Shangguan, Xiaocui Yang, Shi Feng et al.· 0 citations
Humanity's Last Exam (HLE) is widely used to evaluate frontier language models. HLE organizes its questions into eight subject-domain categories, whose subscores are often interpreted as evidence of distinct capabilities. However, no study has assessed whether these labels correspond to empirically separable latent con...
Diffusion Language Models (DLMs) have recently emerged as a promising alternative to autoregressive models. Unlike standard diffusion-based approaches, DLMs are not explicitly conditioned on a timestep, raising a natural question: do these models internally represent denoising progress, and how is such information used...
Maximo Eduardo Rulli, Thomas Vaitses Fontanari, Simone Petruzzi et al.· 0 citations
Humanity is a mosaic of multifaceted talents and needs, and any truly intelligent AI must reflect that richness. Yet the LLMs used by all are built by the few -- a centralized market of monolithic AI models structurally ill-suited to capture the diversity of human knowledge, reasoning, and values. Here we introduce sca...
Shangbin Feng, Yike Wang, Weijia Shi et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Reinforcement learning with verifiable rewards (RLVR) is a scalable paradigm for improving the mathematical reasoning of large language models, but it is fundamentally limited by exploration: the policy can only improve on trajectories it has already sampled. Sampling more rollouts alleviates this at prohibitive comput...
Chanuk Lee, Sangwoo Park, Minki Kang et al.· 0 citations
Retrieval-Augmented Generation (RAG) systems are built on an unexamined assumption - that queries have correct answers and retrieval should converge toward them. This position paper argues that this creates a factual bias where RAG systems optimize for reducing epistemic uncertainty while ignoring the aleatoric uncerta...
Aditya Agrawal, Alwarappan Nakkiran, Aman Singh Thakur et al.· 0 citations
Psychological scale development has traditionally required extensive expert involvement, iterative revision, and large-scale pilot testing before psychometric evaluation can begin. The \texttt{AIGENIE} R package implements the AI-GENIE framework (Automatic Item Generation and Validation with Network-Integrated Evaluati...
Lara Russell-Lasalandra, Hudson Golino, Luis Eduardo Garrido et al.· 0 citations
In agentic search, an LLM agent searches the web, reads the pages it finds, and decides what to look for next before returning an answer. But can we trust an answer simply because the agent returns it? Often not, and even a correct answer can be a lucky guess: on questions with several constraints, we find that agents...
Dayoon Ko, Jihyuk Kim, Sohyeon Kim et al.· 0 citations
In this paper, we study how training data creates associations between the tokens at the start of a base model's response and the reasoning behavior that follows. First, we demonstrate that fixing particular starting token cues makes a base model's performance competitive with that of its reinforcement learning (RL)-tr...
Sophie L. Wang, Amil Dravid, Rulin Shao et al.· 0 citations
LLM agents that orchestrate frozen vision-language-action (VLA) policies improve across episodes through text memory, which records what the agent did but not how the task is done. A demonstration video shows it, but fits poorly into an agent's context. The full video slows every turn, fixed keyframes lose the contact...
Wen-Rui Bao, Xin-Xin Liu, Bing-Xin Xu et al.· 1 citation
A multi-step LLM policy via reinforcement learning is optimized to iteratively choose between retrieving from query-agnostic memory and delegating query-specific curation of raw multimodal history to heterogeneous LLMs and VLMs, enabling fine-grained allocation of runtime computation.
Haozhen Zhang, Hao-Dong Yue, Quan-Yu Long et al.· 0 citations
Open-source web agents are now strong enough to execute realistic browser tasks, but training them with reinforcement learning still depends on weak supervision: binary task success is too sparse for credit assignment, while frontier-language-model judges are too expensive to call at every step and cannot be assumed av...
Yifan Zhang, Yutong Dai, Viraj Prabhu et al.· 0 citations
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
