Category
3,416 papers
The results suggest that LLM data mixing should be treated not only as a prediction problem, but also as an experimental-design problem in which the proxy mixtures themselves can be chosen to improve statistical efficiency.
Agent harnesses record a failed tool call and its error message in the transcript and ask the model to continue, on the assumption that the error is corrective information, and it is found the gain is negative for every instruction-tuned model tested.
This work introduces a general steering technique called Semantic Overlays: small learned adapters applied at chosen prefill positions to a frozen model's residual stream that defends against the broad class of prompt injections that add instructions in untrusted context.
This work introduces Mixture of Channel Experts (MoCE), a structured sparse channel-mixing layer, inspired by MoE, that replaces pointwise (1x1) channel-reduction projections and matches or exceeds dense baselines and prior channel-selection methods while reducing MACs by 16.7% and end-to-end latency.
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work presents MARS (Multi-Agent Relay of Specialized LLMs), a prompt-only framework in which each agent is a topic specialist---dynamic programming, graphs, strings, geometry, and so on---grounded by retrieval-augmented generation over an algorithm-theory corpus.
A reproducible reliability audit of the developer-accessible on-device foundation model is presented, framed as an oversight question: can a user or a resource-constrained developer tell when the model is wrong?
Stochastic analysis sharpens rather than erodes the thesis: the ignition boundary acquires a predicted width, and noise punishes the reactive policy that parks the system against it.
Results show that a small box-level module can reconcile question understanding with precise localization without retraining either backbone, and introduce RefineRank, which closes this gap at the candidate-box level.
Discrete diffusion provides an effective alternative to autoregressive radiology report generation by enabling iterative, bidirectional report refinement.
Whether off-the-shelf Large Language Models (LLMs) can effectively reason about taint flows in Android apps is investigated, and preliminary findings suggest that LLM reasoning may effectively complement traditional static taint analysis.
Results indicate that current LLMs provide uneven safety assurance across Urdu's script varieties, with smaller open-weight models showing substantially higher instability and missed-harm rates than frontier closed models.
This work analyzes a complete corpus of 10,211 inbound scam and spam calls collected over 54 days by an AI voice-agent honeypot that answered callers and kept them talking, and introduced in a companion data descriptor.
A Blog post by Liquid AI on Hugging Face
Genie 4: our new world model unlocking unprecedented realism in real-time simulation.
Generative AI
Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
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 use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
