The deployment of Reinforcement Learning (RL) agents in critical domains must be preceded with a pipeline to evaluate the alignment of the RL agent with complex multi-objective specifications and robustness under real-world environmental drift. However, to protect intellectual property, the RL agent may be delivered fo...
Santhosh GS, Ananya Ravi, Devika Jay et al.· 0 citations
TimeNet provides the data and systems foundation needed to move beyond task- and dataset-specific TFMs toward models that can learn jointly across heterogeneous domains, modalities, temporal scales, and forms of supervision from a common data model.
Martin Maritsch, Timo Stoffregen, Thomas Kaar et al.· 0 citations
Medical language models can produce correct diagnoses despite incomplete investigations and unsupported reasoning. To support long-horizon, evidence-grounded diagnosis, we introduce \textbf{TrustMed-RL}. Built from PubMed rare-disease cases and over 24,000 manually annotated image panels, it integrates interviews, exam...
Wen-Xin Zhan, Yi-Zheng Jiao, Hai-Feng Song et al.· 0 citations
We introduce AgentPersonaBench (APB), a benchmark evaluating whether persona conditioning faithfully steers downstream agent behavior. While language models are increasingly deployed for persona-driven user simulation, existing benchmarks primarily evaluate conversational styling or self-reports rather than authentic b...
Jin-Tao Huang, Yi-Fan Wang, Hong-Yuan Shen et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
IEC-Bench is built from the changes observed in real-world use, with chains of dependent calls under the execution paths of 4 widely-used harnesses, and intent-execution correspondence (IEC) is defined as the property that the executed action matches the action the emitted call denotes under the tool contract.
Bo-Yang Yang, Zhen-Hao Li, Zi-Yao Yang et al.· 0 citations
Determining whether two programs are functionally equivalent is central to code modernization, patch validation, refactoring, and code-generation evaluation. Yet the usual signals are incomplete: tests cover only finite inputs, textual similarity confuses implementation with behavior, and unconstrained LLM judgments ar...
Amit Kachroo, Like Hui, Haitao Mao et al.· 0 citations
ShadowMiner v1 is a system that automatically discovers research problems and generates hypotheses from AI papers. It is a nine-stage pipeline. It structures documents into a knowledge graph and finds graph gaps in it - structural blind spots in research. These graph gaps are included in the LLM generation prompt. Each...
Reliable language models should resist unsupported user pressure while effectively using objective contextual information. However, models may exhibit sycophancy by yielding to unsupported user pressure or contextual stubbornness by failing to update their answers when relevant contextual information warrants revision....
Yinghao He, Mengyu Xu, Haixiang Sun et al.· 0 citations
Correction-based offline preference pipelines commonly treat model failures only as rejected responses under the original prompt. This supervision is incomplete for boundary failures: responses that violate the given instruction yet coherently satisfy a nearby intent or constraint setting. We introduce Bidirectional Pr...
Jun-Bo Wang, Li-Dong Lu, Zhuo-Qun Li et al.· 0 citations
Output-only safety monitoring sees only the end of a model's computation, yet the model computes its answer before emitting it: what it is internally poised to say is safety-critical. Jacobian-space (J-space) readouts, linear maps from hidden states to the output vocabulary via the model's input-output Jacobian, have b...
Long-context decoding is limited by memory bandwidth, because every output token reads the KV cache of every layer. Sparse decoding reduces this cost by reading only part of the KV cache. We observe that the number of pages a query needs varies widely across KV heads, layers and steps. Fixed budgets are simple, but the...
Large datasets and high capacity models have accelerated progress in vision and language. This work introduces a platform aimed at bringing comparable gains to embodied learning, world models, and robotics. We present EnvDreamer, a framework that uses large language and vision language models to generate Unreal Engine...
Kabir Swain, Si-Jie Han, Antonio Torralba· 0 citations
