ICER is a black-box framework that addresses the gap in text-to-image models in harmful content generation through two components: an LLM-based rewriter that produces fluent, natural-language adversarial prompts, and in-context experience replay that accumulates successful jailbreaking patterns into a reusable prior.
Zhi-Yi Chin, Pin-Yu Chen, Wei-Chen Chiu et al.· 2 citations
Looped transformers have demonstrated promising parameter efficiency by reusing layers for latent computation. Prior studies compare looped and non-looped models at matched parameters or per-token FLOPs. However, to the best of our knowledge, whether looping improves test-time scaling as outputs grow longer remains und...
Yi-Chen You, Tianyu Fu, Ao-Song Feng et al.· 1 citation
A language-model agent is jointly defined by its model and its harness, the executable program that organizes model calls, tool use, and information flow. Because different tasks call for different ways of organizing these operations, the harness needs to be adapted using feedback from the task at hand. We introduce ha...
Alvin Zhang, Xue-Chen Liu, Zi-Xuan Wang et al.· 0 citations
A CS-ASR synthetic benchmark and multidimensional evaluation framework tailored to enterprise domains, systematic evaluation of frontier ASR systems across 5 language pairs, and diagnostic analysis of the additional transcription errors that code-switching introduces across language pairs and models are proposed.
Shama Gupta, Hoang Nguyen, Chelsea Huang et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This investigation using an operator-level mechanistic analysis of attention and feed-forward blocks reveals that these blocks systematically ignore MA coordinates while reading, but not while writing; creating a read-write asymmetry that blocks corrective feedback while allowing continued accumulation.
Swagata Mukhopadhyay, Vishal Vivek Saley, Vraj Parikh et al.· 0 citations
We describe the N\"urnberg NLP system for ChildSafeAds 2026. The shared task asks what a monitoring system for commercial content in child-facing YouTube videos can achieve at a given level of data access. We answer with per-subtask ensembles of nine voters, organised into three branches that differ in backbone, adapta...
Philipp Steigerwald, Eric Rudolph, Jens Albrecht· 0 citations
Answer-Convergence Stopping (ACS) is introduced, a training-free stopping rule that measures rather than asks, and reveals that by properly utilizing the output signals of frozen models, it can achieve favorable behaviors like adaptive stopping without the need for additional training.
Muath Alyobi, Mohamed Eltahir, Almoayyad Abuljdail et al.· 0 citations
ReaLVR is proposed, which brings visual-evidence supervision to the model's own free-running latent trajectories, and is the first to scale visual reasoning in latent space, showing that the framework continues to deliver robust improvements at frontier model scales up to 235B.
Xi Xiao, Tian-Chen Zhao, Youngeun Kim et al.· 0 citations
Transformers process tokens without any inherent notion of order, making positional encoding a fundamental requirement rather than an architectural refinement. Rotary Position Embedding (RoPE) has become the default positional encoding in modern language models, yet it is heavily biased toward nearby tokens. Existing a...
Jarod Lévy, Mathurin Videau, Jad Yehya et al.· 0 citations
As large language models (LLMs) become increasingly widespread, preventing unsafe responses to harmful prompts is essential for their safe deployment. Activation steering offers an approach to improving LLM safety by modifying internal activations during inference without updating model parameters. However, a single pr...
Chen-Xi Wang, Rui-Yang Huang, Li Huang et al.· 0 citations
Tail-Corrected Top-$k$ On-Policy Distillation (TT-OPD) is proposed, which preserves the advantages of TK-OPD, including rich distributional supervision and low computational cost, while providing an unbiased estimator of the gradient of the reverse KL divergence.
Lin-Jian Meng, Si-Yuan Gan, Yu-Hang Li et al.· 0 citations
On-policy distillation (OPD) uses teacher correction on student-generated responses. Full-vocabulary correction can provide important corrections even for tokens that the student assigns low probability, but backpropagating through all token logits becomes memory-intensive for long sequences. Existing memory-saving app...
Yongliang Miao, Shuang Liu, Yan-Guang Liu 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.
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Microsoft Research Blog· microsoft.comOct 15, 2026
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.
MIT News · Artificial Intelligence· news.mit.eduSep 24, 2026
