# Mira

Published articles for Mira.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## MIRA: Mitigating Pole Geometry Bias in Recurrent Language Models

DevFeed: [MIRA: Mitigating Pole Geometry Bias in Recurrent Language Models](<https://devfeed.tech/articles/mira-mitigating-pole-geometry-bias-in-recurrent-language-models-124677.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.09412>)

Author: R\\'ois\\'in Luo, Ihsan Ullah, Christian Gagn\\'e, Dong Li, Karyn Morrissey

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [LLM Techniques](<https://devfeed.tech/topics/llm-techniques.md>), [LLM optimization](<https://devfeed.tech/topics/llm-optimization.md>), [context window](<https://devfeed.tech/topics/context-window.md>)

Tags: [architectures](<https://devfeed.tech/tags/architectures.md>), [bias](<https://devfeed.tech/tags/bias.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cuda](<https://devfeed.tech/tags/cuda.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [lattice](<https://devfeed.tech/tags/lattice.md>), [linear](<https://devfeed.tech/tags/linear.md>), [llms](<https://devfeed.tech/tags/llms.md>), [mira](<https://devfeed.tech/tags/mira.md>), [perplexity](<https://devfeed.tech/tags/perplexity.md>), [pretraining](<https://devfeed.tech/tags/pretraining.md>), [recurrent](<https://devfeed.tech/tags/recurrent.md>), [state-space-models](<https://devfeed.tech/tags/state-space-models.md>), [throughput](<https://devfeed.tech/tags/throughput.md>)

### AI overview

MIRA is a linear-time recurrent architecture designed to remove a pole-geometry constraint found in recurrent language-model designs such as selective state-space models, RWKV, and RetNet. Its lattice-ladder blocks implement higher-order IIR systems that can represent temporal modes associated with real and complex-conjugate poles, followed by a feed-forward network. In pretraining, the 12-layer, 0.14B-parameter Mira-S reportedly achieved lower perplexity than strong recurrent baselines, generalized better beyond its training context length, and reached higher throughput with a dedicated CUDA kernel. These are abstract-level claims; the supplied text gives no measurements or experimental details.

### Source excerpt

arXiv:2611.09412v1 Announce Type: new Abstract: We show that the Transformer's recurrent successors --- such as selective state-space models (SSMs), Receptance Weighted Key Value (RWKV), and Retentive Network (RetNet) --- can be characterized as infinite-impulse-response (IIR) systems. The zero--pole geometries of these IIR systems characterize the temporal modes they can represent. However, to trade parallelism, the algebraic structures of the parameterizations of these recurrent systems often give rise to poles constrained to the real axis, thereby inducing an architectural bias in their recurrent dynamics. To unify these recurrent architectures and eliminate their pole geometry bias, inspired by the lattice--ladder realization of general IIR systems, we present \textsc{Mira} (\textbf{M}odal \textbf{I}IR \textbf{R}ecurrent \textbf{A}rchitecture), a unified family of linear-time recurrent architectures for building large language models (LLMs) with a highly parallel algebraic structure. Each \textsc{Mira} block realizes a higher-order IIR system that represents temporal modes from token streams through a lattice--ladder structure, followed by a feed-forward network (FFN). This realization enables the model to represent the temporal modes associated with both real and complex-conjugate poles. We pretrain \textsc{Mira-S}, a 12-layer small-scale LLM with 0.14B parameters composed entirely of \textsc{Mira} blocks. Throughout the pretraining, \textsc{Mira-S} achieves lower perplexity than strong recurrent baselines, exhibits stronger context-window generalization beyond the training length, and attains higher throughput with a dedicated CUDA kernel.

## MIRA: Reinforcing Multimodal Reasoning via Deceptive Contextual Augmentation

DevFeed: [MIRA: Reinforcing Multimodal Reasoning via Deceptive Contextual Augmentation](<https://devfeed.tech/articles/mira-reinforcing-multimodal-reasoning-via-deceptive-contextual-augmentation-115418.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.03087>)

Author: Zhihan Yin, Jianxin Liang, Yifeng Yao, Nonghai Zhang, and Bingyue Peng, Chunguang Qie, Huishuai Zhang, Dongyan Zhao

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [rlvr](<https://devfeed.tech/topics/rlvr.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>)

Tags: [ablation](<https://devfeed.tech/tags/ablation.md>), [annotations](<https://devfeed.tech/tags/annotations.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [error](<https://devfeed.tech/tags/error.md>), [hallucinations](<https://devfeed.tech/tags/hallucinations.md>), [learning](<https://devfeed.tech/tags/learning.md>), [logical](<https://devfeed.tech/tags/logical.md>), [mechanism](<https://devfeed.tech/tags/mechanism.md>), [mira](<https://devfeed.tech/tags/mira.md>), [model](<https://devfeed.tech/tags/model.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [multiple](<https://devfeed.tech/tags/multiple.md>), [policy](<https://devfeed.tech/tags/policy.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [recovery](<https://devfeed.tech/tags/recovery.md>), [reflection](<https://devfeed.tech/tags/reflection.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [rlvr](<https://devfeed.tech/tags/rlvr.md>), [robust](<https://devfeed.tech/tags/robust.md>)

### AI overview

MIRA aims to reduce multimodal models' susceptibility to misleading visual cues, which can compound into hallucinations during reasoning. It trains models with filtered deceptive visual contexts as "hard traps," and uses a group-wise reflection trigger to encourage detection and correction of conflicts between visual cues and logical constraints. The authors say this behavior becomes an intrinsic policy and that the method requires no human annotations. Across multiple reasoning and perception benchmarks, they report an average 7% improvement on in-domain benchmarks and consistent gains on vision-centric benchmarks. The supplied text does not specify the evaluation metrics or individual benchmark results.

### Source excerpt

arXiv:2611.03087v1 Announce Type: cross Abstract: While Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced multimodal reasoning, existing frameworks suffer from a critical "perception-reasoning gap." Due to an over-reliance on seemingly relevant visual tokens, even minor perceptual perturbations can propagate through the reasoning process, leading to compounding hallucinations. To address this issue, we propose MIRA, a training framework that improves robustness to erroneous visual contexts while enhancing logical reasoning ability. By injecting filtered, deceptive visual contexts during training, we construct challenging "hard traps" that stress-test the model's robustness to misleading information. Furthermore, we introduce a group-wise reflection-triggering mechanism that enables the model to autonomously detect and rectify inconsistencies between visual cues and logical constraints, which is ultimately internalized as an intrinsic policy behavior. Importantly, MIRA does not rely on human annotations. Experimental results across multiple reasoning and perception benchmarks show that MIRA yields an average 7% improvement on in-domain benchmarks, with consistent improvements on vision-centric benchmarks. These findings highlight that active error recovery is essential for robust multimodal reasoning. Comprehensive ablation studies and analyses further provide insights into why MIRA is effective.

## MIRA: Mutual Information guided calibration for Reliable Test-Time Adaptation

DevFeed: [MIRA: Mutual Information guided calibration for Reliable Test-Time Adaptation](<https://devfeed.tech/articles/mira-mutual-information-guided-calibration-for-reliable-test-time-adaptation-114627.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.02003>)

Author: Hyeongyu Kim, Mingyeong Jang, Youngjun Song, GeonHui Han, Dosik Hwang

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Data science and engineering](<https://devfeed.tech/topics/data-science-and-engineering.md>), [Hyperparameter optimization](<https://devfeed.tech/topics/hyperparameter-optimization.md>)

Tags: [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [confidence](<https://devfeed.tech/tags/confidence.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [entropy](<https://devfeed.tech/tags/entropy.md>), [errors](<https://devfeed.tech/tags/errors.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [feature](<https://devfeed.tech/tags/feature.md>), [gaussian](<https://devfeed.tech/tags/gaussian.md>), [improvements](<https://devfeed.tech/tags/improvements.md>), [information](<https://devfeed.tech/tags/information.md>), [layer](<https://devfeed.tech/tags/layer.md>), [lightweight](<https://devfeed.tech/tags/lightweight.md>), [local](<https://devfeed.tech/tags/local.md>), [mira](<https://devfeed.tech/tags/mira.md>), [model](<https://devfeed.tech/tags/model.md>), [offline](<https://devfeed.tech/tags/offline.md>), [online](<https://devfeed.tech/tags/online.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [predictions](<https://devfeed.tech/tags/predictions.md>), [test](<https://devfeed.tech/tags/test.md>)

### AI overview

MIRA aims to reduce harmful test-time adaptation by checking how stable predictions are to small perturbations of the classifier's last layer. For each unlabeled target batch, it reuses one feature-extraction pass, samples perturbed classifiers around the source classifier, and selects a batch-specific probing scale using mutual information and prediction agreement. It then weights entropy minimization to reduce the influence of low-confidence or perturbation-sensitive predictions. The method is described as source-free and requiring no retraining, ensembles, or offline posterior fitting. The abstract reports improved accuracy, calibration, and negative log-likelihood on distribution-shift benchmarks, but provides no benchmark details or quantitative results.

### Source excerpt

arXiv:2611.02003v1 Announce Type: new Abstract: Test-time adaptation (TTA) updates a deployed model using only unlabeled target data, but standard entropy-based methods often rely on deterministic confidence and can reinforce overconfident errors under distribution shift. We propose MIRA, Mutual Information guided calibration for Reliable Test-Time Adaptation, a source-free online adaptation method that uses lightweight last-layer Gaussian perturbations to probe prediction reliability. For each target batch, MIRA reuses a single feature extraction pass and samples perturbed classifiers around the source classifier, forming an efficient local predictive distribution. Rather than fitting a Bayesian posterior, MIRA treats the perturbation scale as a local probing radius and selects a batch-specific scale using mutual information (MI) and prediction agreement. The resulting perturbation-sensitivity signal identifies predictions that are confident and locally stable under classifier perturbations, while suppressing brittle predictions with high stochastic disagreement. MIRA then performs adaptation with an MI-confidence weighted entropy loss, which down-weights perturbation-sensitive or low-confidence samples before they drive entropy minimization. This weighted loss reduces the influence of brittle predictions that can otherwise cause harmful adaptation under distribution shift. The method requires no source data, retraining, model ensembles, or offline posterior fitting, and can be applied as a plug-and-play modification to entropy-minimization TTA. Experiments on distribution-shift benchmarks show improvements in accuracy, calibration, and negative log-likelihood, suggesting that mutual-information-guided perturbation probing and weighted adaptation yield more robust online TTA than deterministic confidence.

## World model startup General Intuition closes $220M investment

DevFeed: [World model startup General Intuition closes $220M investment](<https://devfeed.tech/articles/world-model-startup-general-intuition-closes-220m-investment-62225.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/09/29/world-model-startup-general-intuition-closes-220m-investment/>)

Author: Maria Deutscher

Published: 2026-09-30T00:17:42Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [World models](<https://devfeed.tech/topics/world-models.md>), [Training AI Models](<https://devfeed.tech/topics/training-ai-models.md>), [Frontier AI](<https://devfeed.tech/topics/frontier-ai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-training](<https://devfeed.tech/tags/ai-training.md>), [funding-round](<https://devfeed.tech/tags/funding-round.md>), [general-intuition](<https://devfeed.tech/tags/general-intuition.md>), [investment](<https://devfeed.tech/tags/investment.md>), [mira](<https://devfeed.tech/tags/mira.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [news](<https://devfeed.tech/tags/news.md>), [startup](<https://devfeed.tech/tags/startup.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>), [world-model](<https://devfeed.tech/tags/world-model.md>)

### AI overview

General Intuition raised $220 million at a $6.2 billion valuation. The company develops world models that generate synthetic footage for AI training, and its MIRA research demonstration is designed to simulate long-running scenes and interactions useful for training robots. The article describes MIRA's efficiency and notes that it is not currently a commercial training data generator.

### Source excerpt

General Intuition Inc. today announced that it has raised $220 million in funding at a $6.2 billion valuation. The capital was provided by Valor Equity Partners, Atreides, Seven Seven Six, Point72, Khosla Ventures and General Catalyst. The investment comes a year after General Intuition spun out of video sharing startup Medal B.V. Medal provides a [...] The post World model startup General Intuition closes $220M investment appeared first on SiliconANGLE.