As AI agents become increasingly capable of complex, long-horizon reasoning, rigorous evaluation is essential for measuring progress toward real-world healthcare applications. However, existing healthcare benchmarks are often static or narrow in clinical scope, motivating broader evaluation of agents acting on raw pati...
Qianchu Liu, Sheng Zhang, Guanghui Qin et al.· 0 citations
Reinforcement learning with verifiable rewards (RLVR) is widely used to improve the reasoning capability of language models, since model-generated answers can be easily verified by a rule-based verifier. In contrast, reinforcement learning from human feedback (RLHF) is mainly used to optimize open-ended conversation wi...
Shangjian Yin, Yu Fu, Yue Dong et al.· 0 citations
This work identifies the main barrier to adopting compile-and-execute on the web: For it to work well, tools must map cleanly to semantic actions, with effects known before execution, so a compiler has enough information to emit a program.
Julien Piet, Ann T. Chow, Yi Hou et al.· 7 citations· ⚡2
Recent methods for improving LLM mathematical reasoning, whether through MCTS-based test-time search or causal graph-guided knowledge injection, cannot identify which concepts causally contribute to a correct answer, as the observed association may be spurious, driven by confounders such as problem difficulty.
We pro...
Tsuyoshi Okita· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Weight matrices in deep networks exhibit geometric continuity---principal singular vectors of adjacent layers point in similar directions. While this property has been widely observed, its origin remains unexplained. Through experiments on toy MLPs and small transformers, we identify two mechanisms: residual connection...
Large-scale sign language resources usually pair RGB videos with text and support recognition, translation, and generation. However, RGB frames contain backgrounds, clothing, and other appearance information unrelated to signing motion. Representing the videos as whole-body keypoints such as DWPose removes much of this...
Sen Fang, Hongbin Zhong, Yanxin Zhang et al.· 0 citations
Self-supervised learning (SSL) underpins modern audio deepfake detection, yet most prior work centers on a single large wav2vec2-XLSR backbone, leaving compact under studied. We present RAPTOR, Representation Aware Pairwise-gated Transformer for Out-of-domain Recognition a controlled study of compact SSL backbones from...
Ajinkya Kulkarni, Sandipana Dowerah, Atharva Kulkarni et al.· 0 citations
Large language models (LLMs) increasingly rely on external knowledge to improve factuality, yet many knowledge sources on the Web, such as scholarly indexes and product catalogs, are organized as heterogeneous graphs. Reasoning over such graph-structured knowledge poses two key challenges: (1) navigating structured, sc...
Yuyang Bai, Zhuofeng Li, Ping Nie et al.· 0 citations
Scientific discovery requires new ideas to be situated within an ever-expanding landscape of existing knowledge. An emerging challenge is how to identify conceptually relevant prior work from rapidly growing literature, and assess how a new idea differentiates from existing research. Current embedding approaches typica...
Minqian Liu, Yuexi Shen, Dawei Zhou et al.· 0 citations
The emergence of Large Language Models (LLMs) and advancements in Artificial Intelligence (AI) offer an opportunity for computational social science research at scale. Building upon prior explorations of LLM agent design, our work introduces a simulated agent society where complex social relationships dynamically form...
Gordon Dai, Weijia Zhang, Jinhan Li et al.· 0 citations
A prompt is an instruction or description provided by the user to guide a generative language model toward outputs that meet application requirements. When these requirements change, existing prompts may need to be adapted and improved. Evaluating candidate prompts requires time and computational resources. We therefor...
Haoting Zhang, Jinghai He, Rhonda Righter et al.· 0 citations
As LLMs expand their language coverage, evaluating how well they understand and represent diverse cultures becomes increasingly important. However, many benchmarks remain English-centric, with limited cultural coverage and a focus on factual knowledge over its application in real-world cultural contexts. We propose Cul...
My Chiffon Nguyen, Tianyi Hu, Vinod Anbalagan et al.· 0 citations
