Medical Vision-Language Models (Med-LVLMs) have shown strong performance in Medical Visual Question Answering (MVQA), yet they may still produce factually inconsistent responses. Retrieval-Augmented Generation (RAG) can mitigate this issue by incorporating external clinical evidence; however, retrieval is often guided...
Daniela Jimenez-Pano, Hugo Jair Escalante, Delia Iraz\'u Hern\'andez-Far\'ias· 0 citations
A memory test for a video world model should say whether the scene was set, whether the asked change was carried out, and whether the last frame shows the result. Current tests fold these into one number, so a low score is easy to read as forgetting. When the change is not carried out, the hidden state transition canno...
Weiyang Jin, Jiwen Yu, Sihan Xu et al.· 0 citations
It is proved that a fixed Cohen's kappa leaves a law nearly unconstrained, and that Threadsafe uses the labeler's scores to choose which comments human raters label and to predict the others, and corrects the predictions with the human labels; linear laws are estimated without bias whatever the labeler does.
Efficient expert routing is a fundamental challenge in Mixture-of-Experts (MoE) systems, particularly for heterogeneous collections of independently trained Large Language Mod els (LLMs). Existing routing approaches typically rely on jointly trained gating networks, prompt-based predictors, or computationally expensive...
Rajdeep Pandhare, Delzaan Bharucha· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Tool-augmented language-model agents rely on interface text: tool descriptions, argument schemas, and the candidate tool list shown at inference time. These interfaces often change after deployment even when the underlying tool semantics remain fixed, creating a practical reliability problem for function-calling system...
Large language models (LLMs) can generate fluent outputs that lack source support or conflict with local operational constraints. We introduce Self-Reflective Chain-of-Thought (SRCoT), a modular architecture that organizes generation as a closed Retrieve--Reflect--Revise loop. SRCoT separates environment state, persist...
Fabian Broszio, Michael Hoffmann, Adrian Paschke· 0 citations
A key challenge in on-policy distillation (OPD) is extracting effective supervision from teacher knowledge. Supervision from token probabilities may underutilize internal knowledge, while direct hidden-state matching forces the student to shift to the teacher's feature space and complicates cross-architecture transfer....
Kai Tang, Xing Zheng, Haobo Wang et al.· 0 citations
Annotrace measures agreement between any two annotators, human or AI, and reads six trace formats, including OpenTelemetry GenAI, LangSmith and Langfuse, and turns each run into an ordered, nested list of steps.
Arun Josephraj Arokiaraj, Chen Huang, Bin Wu et al.· 0 citations
Large language model chatbots have been proposed as AI-interviewers for collecting qualitative interview data at scale, potentially bridging social science's longstanding divide between the breadth of surveys and the depth of qualitative interviews. This paper provides the first direct empirical comparison of data qual...
S. Güven, T. Gårdhus, Andreas Bjerre-Nielsen et al.· 0 citations
This work proposes ECHO (Evaluation-Conditioned Harmfulness Optimization), which replaces the compliance proxy with response-level, continuous harmfulness scores from HarmSig, a 1.7B regressor grounded in actual harmful capability.
Yuan-Wei Wu, Ling-Dong Huang, Yun-Long Mao et al.· 0 citations
SAFE-Mem is a fine-grained memory governance framework that improves security while preserving legitimate memory use and attains the lowest attack success among defenses that retain legitimate memory, at least 77% below the strongest of them, and the highest answer accuracy of all evaluated defenses.
Hao-Ming Li, Ding-Yi Kang, Xue Hu et al.· 0 citations
Large Language Models (LLMs) have demonstrated remarkable success in complex reasoning through explicit Chain-of-Thought (CoT), but the associated computational overhead and token verbosity remain significant barriers to efficiency. While implicit reasoning in continuous latent spaces offers a promising alternative, ex...
Yin-Long Xu, Jian-Feng Huang, Zheng-Dong Zhou 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.
