Category
8,908 papers
Benchmarks for vision-language models offer their answer choices in some convention: a letter, a color name, a pixel coordinate. That convention is treated as neutral. We find it is not, and that the limits a benchmark reports can belong to the readout rather than to the model. On 200 COCO photographs, Qwen3-VL-4B pi...
TRAD, an audit grid crossing 120 texts, 24 rendered demographic voice profiles, and ten expressive styles via controllable text-to-speech, isolating perceived demographic attributes from content and affect is introduced.
End-to-end speech-to-speech dialogue models listen and speak simultaneously, so a continuously open acoustic channel is exposed to adversarial manipulation. We formalize imperceptible attacks on full-duplex agents as optimization over additive perturbations confined beneath the psychoacoustic masking threshold of the c...
Language-model agents increasingly face long-horizon tasks with evolving state, interdependent decisions, and delayed outcomes, and scale-matched training retains gains as mechanism size and horizon grow, indicating the potential for an evolving training substrate.
Reach audiences
Advertise in front of researchers, engineers, and readers.
The Large Knowledge Model is proposed, a growing, agent-native knowledge foundation that provides a general representation of scientific knowledge across disciplines and an agent-native, reasoning-aware scientific retrieval system that retrieves claims together with their reasoning chains and sources, enabling agents t...
Results show that entity-structured indexing and episode-level provenance provide a reliable foundation for long-term memory in agents, and EnSIMem achieves high answer accuracy while maintaining compact, evidence-focused contexts.
CAVEAT-Harness is developed, which targets failures and raises the optimal purchase rate by up to 80.0 percentage points, and targeted post-training further improves a smaller open model, to establish incentive robustness as a distinct challenge for delegated agents and diagnose failure modes.
Non-speech interference can change a speech representation without causing comparable task loss. We test eight frozen encoders on four tasks, adding non-speech sounds throughout recordings, during speech, or in pauses. Under whole-recording interference, embedding drift tracks task loss across seven sounds, with mean S...
ContraVis is presented, a visual analytics system for human-in-the-loop contradiction analysis in legal contracts that models contracts as typed paragraph graphs that combine explicit contractual references with semantic relationships between paragraphs.
This work studies two questions: when can one model improve two objectives simultaneously, and how can many trade-offs be covered without training a separate model for each?
Text-output scores alone do not show whether quantization preserves performance on speech tasks whose target labels cannot be recovered from the transcript. We evaluate fixed mixed 4/8-bit Qwen2-Audio-7B-Instruct allocations averaging 6 and 7 bits per parameter on 508 English-to-German FLEURS utterances and on 512 RAVD...
A sequential low-rank adaptation protocol for cross-scale transfer that attains the best point-estimate MAE, RMSE, and macro-$F_1$ on both 0.6B and 1.7B backbones, outperforming target-only training and non-LLM baselines.
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.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
A new language-processing tool could help identify the highest-risk individuals from natural language, enabling swifter interventions.
A Blog post by Liquid AI on Hugging Face
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
