AI News Archive: August 12, 2026 — Part 18
Sourced from 500+ daily AI sources, scored by relevance.
- Clustered Randomized Smoothing for Stochastic Prediction Functions
Modern stochastic predictors can model rich, multi-modal outcome distributions. However, this expressive power comes with challenges in ensuring robust predictions $-$ a critical requirement in safety-critical domains. Randomized smoothing is a leading technique for improving robustness, particularl...
- SoftWater: Class-Aware Rate Allocation for Softmax Quantization
Post-training quantization pipelines routinely leave the softmax output layer in high precision. Yet in small LLMs with modern vocabularies, the head holds 15--30\% of all parameters, so a nominal ``2-bit'' model with an fp16 head can store several times as many bits per weight. We pose softmax-laye...
- Reducing Symmetry Increase in Equivariant Neural Networks
Equivariant Neural Networks (ENNs) have empowered numerous applications in scientific fields. Despite their remarkable capacity for representing geometric structures, ENNs suffer from degraded expressivity when processing symmetric inputs: the output representations are invariant to transformations ...
- TESLA: Taylor Expansion of Sinusoidal Learnable Activations
The parity problem--deciding whether the number of ones in a binary vector is odd or even--remains challenging for standard neural networks due to linear inseparability and the need for global interactions. We propose TESLA, an activation defined as a learnable combination of sine and cosine terms, ...
- LoongReflect: Boosting Long-Horizon Reflection in Search Agents via Global Perspective Distillation
Large language model agents increasingly rely on long-horizon reasoning to solve complex tasks involving planning, tool use, and memory. A critical capability in such settings is reflection: assessing trajectory progress, identifying missing evidence and unreliable intermediate states, and deciding ...
- TailBooster: A Dual-Layer Generative Framework for Extreme Value Augmentation with Operational Validity Enforcement
Extreme events in air transport, such as severe arrival delays and abnormal air times, cause cascading network disruptions with substantial operational, economic, and safety costs. Such events are rare in historical records, leaving insufficient training signal for machine learning models. Synthetic...
- Distillation of Foundation Models for Time-dependent PDEs
Foundation models for time-dependent partial differential equations (PDEs) are trained on large and diverse collections of physical systems and can generalize effectively to new downstream tasks. After fine-tuning on only a few trajectories from a target domain, they can achieve strong accuracy in l...
- A Framework for Designing Reward Functions: From Objectives to Features to Human-Aligned Reward Functions
We present a formal process to enable non-experts to instantiate and iterate on human-aligned reward functions, i.e. reward functions that adhere to a given preference ordering over trajectories. Given a task described in natural language, our process produces a linear reward function in three steps...
- An Efficient Near-Optimal Algorithm for Adversarial $m$-Set Bandits
We study adversarial combinatorial bandits with $m$-set actions, where at each round the learner selects $m$ out of $d$ items and observes only the aggregate loss of the selected items. The resulting action set contains $K=\binom{d}{m}$ elements and can therefore be exponentially large. Nevertheless...
- FQTree: Fine-grained Quantization and Hardware Generation of Boosted Decision Trees
Boosted decision trees (BDTs) are widely used in latency-critical applications, but efficient hardware deployment remains challenging. Existing designs often rely on uniform or manually tuned fixed-point formats, which can introduce unnecessary hardware cost or accuracy loss. This work presents the ...
- NAE: Normalizing AutoEncoder
We consider the setting of Normalizing flows with approximate inverses, an established paradigm spanning both full-dimensional ($d=D$) and bottleneck ($d<D$) settings, and group these models under the term flow autoencoders. We present a theoretical investigation into their training dynamics and pro...
- Towards Truly Unsupervised Evaluation of Feature Selection
Feature selection is one of the most important and fundamental tasks in data mining, tackled by a family of methods with an established set of evaluation techniques to measure the quality of a specific method. Most of the methods commonly used for the unsupervised evaluation of feature selection alg...
- Beyond Local Power: Functional Connectivity Analysis for Subject-Independent Learning Style Recognition
Identifying individual learning styles optimizes pedagogical efficacy. While traditional questionnaires are structured, behavioral tracking methods require prolonged interaction log accumulation. To overcome these temporal constraints, this paper proposes an objective Electroencephalography (EEG) ap...
- A Factor Graph Approach to Scalable Multi-Output Gaussian Process Regression
Multi-output Gaussian process regression scales cubically in the number of observations times outputs, and dense kernel-matrix methods need bespoke handling whenever different outputs are observed at different inputs. We express multi-output Gaussian process regression as a Forney-style factor graph...
- Disentangling the Expressivity of RoPE
Two accounts recur in explanations of the success of rotary position embeddings (RoPE). Expressivity studies associate periodic position information with modular predicates, whereas mechanistic and long-context studies emphasize positional anchors and local offsets. We formalize both accounts for fu...
- Policy-as-logic for robust reasoning over rules
In many practical applications of generative AI systems, from tax rules to airline baggage allowance, responses to natural language queries must respect written policies or rules. We present a hybrid symbolic approach that expresses policies in formal logic and at inference time exploits the represe...
- DCM Bandits: Multiplayer Information Asymmetric Cascading Bandits for Multiple Clicks
In this work, we extend the Dependent Click Model (DCM) Bandits to a multiplayer information-asymmetric setting, where multiple agents interact with a shared ranked list and may observe multiple clicks per session, introducing new challenges for selection strategies. We study asymmetry in (1) action...
- StellaVLA: In-Context Structured Demonstration for Generalizable Vision-Language-Action Models
Vision-Language-Action (VLA) models can follow instructions and manipulate objects, but their performance often collapses out of distribution (OOD), when the scene, viewpoint, or object differs from training. Adapting to each new situation typically requires collecting more data and fine-tuning. We ...
- RoadWeaver: Large-Scale Lane-Level HD Map Generation from Scratch for Autonomous Driving Simulation
Autonomous driving simulation requires diverse and scalable lane-level HD maps to support long-horizon evaluation across complex road networks. Existing approaches either rely on handcrafted or reconstructed real-world maps, which limits scalability, or generate only local road structures rather tha...
- Repurposing RGB-based Foundation Model for Depth Estimation on Thermal Images Using Hierarchical Supervision
Depth estimation from thermal images is highly valuable for robotic applications in adverse conditions, such as nighttime and rainy weather. Recent studies have sought to transfer knowledge from RGB-based foundation models to thermal modalities, yet the rich hierarchical representations these models...
- DaViNCi: A Dataset Towards Outdoor Vision-and-Language Navigation with Continuous Actions and Dynamic Elements
Vision-and-Language Navigation (VLN) has progressively expanded from indoor to outdoor environments. However, existing outdoor VLN datasets still rely on fixed discrete topological graphs for construction. It fails to align with the rapidly changing real-world outdoor environments and impedes the si...
- Scalable Multi-Agent Maze Traversal with Local Communication
Cave networks, pipe systems, and similar maze-like environments pose significant challenges for multi-agent navigation in unknown settings with limited communication. We propose a distributed algorithm that enables agents to collectively traverse an unknown, possibly cyclic graph. Agents enter seque...
- D3D-GEN: Robot-Aware Domain-Grounded Interactive 3D World Generation for Social Robotics
Training and validation of Embodied AI for social navigation critically depends on realistic simulation environments, yet many current approaches fail to find a balance between realism and simulability. We propose D3D-GEN, a novel world generation system that combines a domain agent with a retrieval...
- Enhancing Visual Domain Robustness in Behaviour Cloning via Saliency-Guided Augmentation
In vision-based behavior cloning (BC), conventional image augmentations such as Random Crop and Color Jitter often fall short under substantial visual domain shifts, including changes in shadows, distractors, and backgrounds. Superimposition-based augmentations, which blend in-domain and out-of-doma...
- Policy-Induced Hand Priors in Humanoid Dual-Arm Manipulation: Diagnosing and Mitigating Initial-Pose Dependence
Vision-language-action (VLA) policies are expected to operate robustly across variations in the robot's initial configuration, yet aggregate task success can conceal pose-specific failures and inappropriate hand selection. This work investigates initial-pose dependence in VLA-based humanoid dual-arm...
- G0.5: One Autoregressive Stream for Robot Reasoning and Action
The prevailing recipe for Vision-Language-Action (VLA) models couples a pretrained VLM with a separately trained flow-matching action expert. This makes the VLM a context encoder rather than a decision-maker. We introduce G0.5, a pretrained autoregressive VLA in which a single transformer decoder em...
- IoT-Enabled Autonomous Maritime Navigation in Smart Ports: A Curriculum-Guided Shared Policy Learning Framework
As smart port infrastructures increasingly rely on autonomous maritime devices enabled by the Internet of Things (IoT), ensuring reliable onboard navigation intelligence has become a critical challenge for safe and scalable operations in congested waterways. This paper investigates onboard autonomou...
- Video2Track: From Real-World Interaction Videos to Steerable Adversarial Closed-Track Testing for Automated Driving Systems
Closed-track testing plays a fundamental role in the verification and validation of automated driving systems (ADS), particularly for safety-critical scenarios, by enabling reproducible evaluation under controlled conditions. However, most existing approaches still rely on standardized protocols or ...
- Keep the Future, Drop the Rollout: RIFT for World Action Models
World action models (WAMs) condition robot actions on predicted futures, but iterative video rollout increases deployment latency. We ask whether action generation requires the evolving rollout trajectory or only its future representation. Across four WAMs on all 40 LIBERO tasks, paired closed-loop ...
- Kernel Methods for Learning Operators with Multiple Inputs and Outputs
Learning mappings between infinite-dimensional objects is a central challenge in scientific machine learning. We introduce a general kernel-based encoder-decoder framework for operator learning that separates observation, representation, learning, and reconstruction. We develop this framework for mu...
- Fine-Tuning Generative Models for Extreme Events via CVaR-Penalized Wasserstein Gradient Flows
We propose CVaR-penalized Generative Particle Algorithm (CVaR-GPA), a robust, tail-agnostic algorithm for fine-tuning generative models to learn heavy-tailed distributions and capture extreme events, requiring no prior knowledge or estimation of the target's tail characteristics. The method is the W...
- Coarsening Latent-Class Probabilities: Directional Distortion and Coverage Loss
Outcomes are increasingly regressed on a calibrated probability vector for unobserved class membership, and that vector is often coarsened to a hard label first. Under a constant-coefficient structural mean and conditional calibration, the observed-data problem is a partially linear regression of th...
- MOON: Multi-Objective OrthoNormalized Updates for Multitask Learning
Multi-objective optimization (MOO) has demonstrated significant success in multi-task learning by mitigating task conflicts through gradient manipulation. However, most existing methods flatten model parameters into vectors and perform gradient manipulation under Euclidean geometry, thereby overlook...
- Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning
Continual learning must absorb new tasks without erasing old ones, and replay---mixing a small buffer of past examples into current training---is among the most effective remedies for catastrophic forgetting. Yet its generalization behavior is shaped by two coupled effects that existing analyses fol...
- Dograh
The open source VAPI alternative
- Grok Bot
AI teammates that you can give real work to
- Lettertrace
Track your AI visibility for free (using your own API keys!)
- Assembly Studio
AI app builder that grows your revenue
- Unsloth Desktop
Run and train AI models locally on your desktop
- BearDrive
The open-source shared folder for your team's AI agents
- Swipe
Swipe right on your next customer
- Click
Live research context for ChatGPT and Claude
- LaraCopilot
Agentic AI Engineer that builds real apps
- RightCard
The honest credit card picker — no bank login
- CodeBurn
See where your AI coding spend actually goes
- Media Sharing
Let AI agents put screenshots and videos on pull requests
- Chat Agent by Trigger.dev
AI chat that keeps running after you close the tab
- Nearfield
Turn two or more Studio Displays into stereo speakers
- Statewave
Open-source memory runtime for production AI agents.
- Cleanup
Erase unwanted objects from photos in seconds