Continuous diffusion models have emerged as a promising non-autoregressive paradigm for text generation over continuous embedding spaces. Along the continuous trajectory, the residual token identity directly shapes the denoising objective. However, the geometric trajectory misaligns with temporal progression, triggerin...
Zijian Jia, Peixuan Zhang, Genying Li et al.· 0 citations
This paper proposes incorporating channel configuration (CFG) information into Radio Foundation Model (RFM) pre-training and demonstrates that the resulting CFG-enriched embeddings serve as effective inductive priors for downstream tasks under label scarcity. We compare the proposed embeddings with raw channel tokens a...
Shrihari Vasudevan, H. G. Ranjani, Raaghul Ranganathan et al.· 0 citations
GUI grounding benchmarks ask whether an agent can localize a target that is already visible in a static screenshot. Real interfaces often violate this assumption: a target may be off-screen, appear only after a state change or hover, remain occluded, or become actionable after a delay. This leaves the ability to recove...
Kyeongseon Kim, Jiyeon Son, Tae-Hyun Oh· 0 citations
LLM agents combine models with execution harnesses, so agentic benchmark performance reflects their joint behavior. We argue that harnesses should therefore be evaluated through their interactions with underlying models. We develop a framework combining five complementary measures: (i) Valid Completion Rate (VCR), how...
Shao Zhang, Hang-Fan Zhang, Yuan-Yuan Shi et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
CASE maintains a sparse, self-evolving library of pair-specific EmotionSkills that externalize affective expertise from model parameters, enabling the learned expertise to be continuously refined and readily transferred across diverse frozen MLLM backbones.
Si-Yu Wu, Ze-Yu Liang, Ling-Hao Wang et al.· 0 citations
Large language model (LLM) agents increasingly support long-horizon tasks by leveraging external memory and past experience. However, existing agents mainly retrieve records or summaries, lacking the ability to form and refine causal understanding of the world. Inspired by human causal cognition, we introduce CauProphe...
Advances in Multimodal Large Language Models (MLLMs) have driven substantial progress in multimodal embeddings. Recent methods exploit generative capabilities by augmenting embedded inputs with self-generated reasoning to produce more informative embeddings. However, conventional retrieval supervision for training embe...
Tian-Yu Yang, Yi-Jun Tian, Lars Benedikt Kaesberg et al.· 0 citations
Telephone triage is a safety critical task: from a brief intake note, a nurse must decide whether a caller needs an ambulance, an emergency department, an appointment, or self care at home. Queried directly, large language models (LLMs) are unreliable: they over-escalate routine cases and cannot justify their recommend...
M. Janiszewski, Artur Stopa, Lukasz Lenkiewicz et al.· 0 citations
Training environments remain a major bottleneck for agents in data-driven scientific discovery. Existing collections of executable and verifiable training environments are small, and their construction remains difficult to scale. To address this limitation, we introduce Poseidon, an automated pipeline for generating di...
Qifan Zhang, Yuhan Li, Nuo Chen et al.· 0 citations
A failed vision-language-action (VLA) rollout does not imply that every action contributed to failure. Yet in group-relative policy optimization (GRPO), a single trajectory-level advantage is assigned to all actions in a rollout. Potentially useful recovery attempts can thus be penalized alongside the errors they aim t...
Zongyao Zhao, Cheng-Jie Zhao, Ruihang Jiang et al.· 0 citations
The challenges of reliable asynchronous task execution in LLM agents are highlighted and the need to evaluate how agents handle incoming results alongside end-to-end task success is highlighted.
De-Tao Zeng, Gui-Lin Ou, Nuo Chen et al.· 0 citations
Recursive large language model (LLM) agents solve long-horizon tasks through decomposition, execution, and environmental feedback. Yet after producing an atomic subtask, they often invoke the same large model again to translate a familiar instruction into an executable action. We observe that high-level planning is tas...
Sheng-Chang Liu, Ze-Xin-Yi-Chun Zhou, Zhen-Guo Xu et al.· 0 citations
