model releases

RAIL: Rethinking Auditory Intelligence in Large Audio-Language Models with a CHC-Grounded Benchmark

arXiv:2606.11260v1 Announce Type: cross Abstract: Humans process rich auditory environments through tightly integrated cognitive capabilities such as audio perception, audio reasoning, and memory. Des

Model Releases

Range-Aware Bayesian Optimization for Discovering Diverse Designs within Target Property Windows

DGX agent

arXiv:2606.11574v1 Announce Type: new Abstract: In many materials and product design problems, desirable candidates exhibit properties that fall within an acceptable range rather than achieve a single

model-releasesarxiv-cs-lg

11 Jun 2026

RankVR: Low-Rank Structure Perception and Value Recalibration for Robust Composed Image Retrieval

arXiv:2606.11689v1 Announce Type: new Abstract: Composed Image Retrieval (CIR) constitutes a pivotal paradigm requiring models to perform joint reasoning on reference images and modification texts. Ho

Reassessing High-Performing LLMs on Polish Medical Exams: True Competence or Bias-Driven Performance?

arXiv:2606.12250v1 Announce Type: new Abstract: Large language models (LLMs) in medicine are mainly evaluated using multiple-choice question answering (MCQA), which can overestimate real clinical abil

ReMoT: Reinforcement Learning with Motion Contrast Triplets

arXiv:2603.00461v3 Announce Type: replace Abstract: We present ReMoT, a unified training paradigm to systematically address the fundamental shortcomings of VLMs in spatio-temporal consistency -- a cri

Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models

arXiv:2606.12412v1 Announce Type: cross Abstract: Vision-language models (VLMs) project images into hundreds to thousands of visual tokens, making decoder inference expensive in both attention computa

Restless bandits with imperfect binary feedback: PCL-indexability analysis and computation

arXiv:2606.11192v1 Announce Type: new Abstract: We study restless bandits with binary latent states and imperfect binary feedback, motivated by opportunistic spectrum access with sensing errors. For t

Robust Privacy: Inference-Stage Privacy through Certified Robustness

arXiv:2601.17360v2 Announce Type: replace-cross Abstract: An adversary observing a model's released prediction can infer sensitive attributes of the queried input, or even reconstruct representatives

Robustness of Mixtures of Experts to Feature Noise

arXiv:2601.14792v2 Announce Type: replace Abstract: Despite their practical success, it remains unclear why Mixture of Experts (MoE) models can outperform dense networks beyond sheer parameter scaling

RoVE: Rotary Value Embeddings Attention for Relative Position-dependent Value Pathways

arXiv:2606.11275v1 Announce Type: cross Abstract: Rotary Position Embeddings (RoPE) make attention scores position-relative but leave the value pathway position-blind: the message sent by a value toke

RSTR: Reducing SpatioTemporal Redundancy in Diffusion Transformers

arXiv:2512.14096v2 Announce Type: replace Abstract: Diffusion Transformers (DiTs) have achieved remarkable success in image generation, yet their deployment is hindered by high computational costs. We

Running Gemma 4 QAT 12B on an 8GB GPU at 16k context — measured the KV-cache tradeoffs

This post discusses running Google's Gemma 4 QAT (Quantized Aware Training) 12B model on a GPU with 8GB of memory while maintaining a 16k token context window. The author likely shares performance ben

model-releasesr-ollama

Scaling Laws of Global Weather Models

arXiv:2602.22962v2 Announce Type: replace Abstract: Data-driven models are revolutionizing weather forecasting. To optimize training efficiency and model performance, this paper analyzes empirical sca

SceneMiner: Identity-Preserving Multi-Task Fine-Tuning for Unified BEV Scene Mining

arXiv:2606.11507v1 Announce Type: new Abstract: Mining hard, safety-critical scenes from driving logs is bottlenecked by the absence of difficulty labels, and no single proxy, collision risk, trajecto

SheafStain: Sheaf-Theoretic Schrodinger Bridge for Spatially and Biologically Coherent Virtual Staining

arXiv:2606.11846v1 Announce Type: new Abstract: Current virtual staining approaches offer the potential for time- and cost-efficient biomarker quantification in cancer diagnostics and prognostics. How

Simplicity Suffices for Parameter Noise Injection in Stochastic Gradient Descent

arXiv:2606.12054v1 Announce Type: new Abstract: Injecting noise into the optimization process is a well-established technique for improving the training and generalization of deep neural networks. Yet

SirenFNO: Efficient and Full Frequency Learning of Fourier Neural Operators

arXiv:2606.11518v1 Announce Type: cross Abstract: Fourier neural operators (FNOs) are effective and efficient surrogates for approximating solutions of PDEs and generalize across discretizations. Howe

Soft-Prompt Tuning for Fair and Efficient LLM Benchmark Evaluation

arXiv:2606.12117v1 Announce Type: cross Abstract: Benchmark scores often misrepresent a large language model's (LLM's) knowledge, because they rely, e.g., on the model's ability to follow specific for

SoftMatcha 2: A Fast and Soft Pattern Matcher for Trillion-Scale Corpora

arXiv:2602.10908v2 Announce Type: replace Abstract: We present SoftMatcha 2, an ultra-fast and flexible search algorithm that enables search over trillion-scale natural language corpora in under 0.3 s

Sparse probes and murky physics: a case study of interpretability challenges in a foundation model for continuum dynamics

arXiv:2606.11657v1 Announce Type: cross Abstract: Generative AI emulators are increasingly used in scientific domains where we already have strong theory, benchmarks, and physical intuition. This rais

Sparsified Kolmogorov-Arnold Networks for Interpretable Quantum State Tomography

arXiv:2606.11814v1 Announce Type: cross Abstract: Machine-learning approaches to quantum state tomography can achieve high reconstruction fidelity, but the physical structure used by the trained model

Spatially Coupled Phase-to-Depth Calibration for Fringe Projection Profilometry

arXiv:2606.11601v1 Announce Type: new Abstract: In fringe projection profilometry (FPP), depth is commonly recovered by fitting a phase-to-depth relation independently at each camera pixel. Although s

SPEA2^+: Improved Density Estimation in SPEA2 with Provable Runtime Guarantees

arXiv:2606.12382v1 Announce Type: cross Abstract: The Strength Pareto Evolutionary Algorithm 2 (SPEA2) is a popular and prominent evolutionary algorithm for solving multi-objective optimisation proble

SPEAR: A System for Post-Quantization Error-Adaptive Recovery Enabling Efficient Low-Bit LLM Serving

arXiv:2606.11244v1 Announce Type: cross Abstract: Efficient large language model (LLM) serving is increasingly constrained by deployment cost. Quantization is a key technique for reducing serving cost

STEAM: Squeeze and Transform Enhanced Attention Module

arXiv:2412.09023v3 Announce Type: replace Abstract: Channel and spatial attention mechanisms introduced in earlier work enhance the representational capabilities of deep convolutional neural networks

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning

arXiv:2601.04710v2 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) achieves strong performance but is often limited by the memory overhead of backpropagation. Zeroth-order (Z

Substrate Asymmetry in User-Side Memory: A Diagnostic Framework

arXiv:2606.11712v1 Announce Type: cross Abstract: User-side memory in LLMs is typically scored as a single 'personalization' capability: given a user's history, is the output more user-aware? We show

SwiftCTS: Fast Cross-Design Prediction and Pareto Optimization of Clock Tree Metrics via Few-Shot Calibration

arXiv:2606.11348v1 Announce Type: new Abstract: Clock Tree Synthesis (CTS) is a computationally expensive stage in the physical design flow, requiring iterative EDA tool invocations to navigate a vast

System Report for CCL25-Eval Task 5: New Dataset and LoRA-Fine-Tuned Qwen2.5

arXiv:2606.12392v1 Announce Type: cross Abstract: Recently, large language models (LLMs) have achieved promising progress in the fields of classical Chinese translation and the generation of classical

Tac-DINO: Learning Vision-Tactile Features with Patch Alignment

arXiv:2606.12069v1 Announce Type: new Abstract: Touch is the primary medium through which humans interact with the environment. Currently, tactile learning mainly focuses on image-level pretraining or

TAHOE: Text-to-SQL with Automated Hint Optimization from Experience

arXiv:2606.12387v1 Announce Type: cross Abstract: Large Language Models (LLMs) have democratized database access through Text-to-SQL, but moving from prototypes to production remains difficult. Real d

Task-Aligned Stability Analysis of Vision-Language Models for Autonomous Driving Hazard Detection

arXiv:2606.11889v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly used for scene understanding in autonomous driving, but robustness analysis often relies on task-agnost

Teaching Diffusion to Speculate Left-to-Right

arXiv:2606.11552v1 Announce Type: new Abstract: Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their autoregressive decoding process incurs substantial i

The Language You Ask In: Language-Conditioned Ideological Divergence in LLM Analysis of Contested Political Documents

arXiv:2601.12164v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed as analytical tools across multilingual contexts, yet their outputs may carry systemati

The model subsidies will eventually end and this workflow of “creating loops that will prompt your agents” will result in massive amounts of…

model-releasesjerry-liu--x

The model subsidies will eventually end and this workflow of “creating loops that will prompt your agents” will result in massive amounts of code that’s not well understood that you will have to pay l

The N-Body Problem: Parallel Execution from Single-Person Egocentric Video

arXiv:2512.11393v2 Announce Type: replace Abstract: Humans can intuitively parallelise complex activities, but can a model predict this from observing a single person? Given one egocentric video, we i

The Standard Interpretable Model: A general theory of interpretable machine learning to deductively design interpretable methods using Lagrangian mechanics

arXiv:2606.12289v1 Announce Type: cross Abstract: As Artificial Intelligence models grow in complexity, interpretability has become an indispensable tool for understanding, debugging, and controlling

The Structural Attention Tax: How Retrieval Format Hijacks In-Context Learning Independent of Content

arXiv:2606.11198v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) systems inject external knowledge to improve LLM outputs, yet the format of injected content -- distinct from its

Time-multiplexed layer reuse for physical neural networks

arXiv:2511.00044v3 Announce Type: replace Abstract: Physical neural networks (PNNs) are promising candidates for next-generation computing, but existing demonstrations remain several orders of magnitu

Time-Series Foundation Model Embeddings for Remaining Useful Life Estimation

arXiv:2606.11990v1 Announce Type: cross Abstract: Remaining Useful Life (RUL) prediction is essential for industrial predictive maintenance, yet many learning-based approaches rely on extensive featur

TimeRouter: Efficient and Adaptive Routing of Time-Series Foundation Models

arXiv:2606.11625v1 Announce Type: new Abstract: Time-series foundation models (TSFMs) are increasingly explored as predictive experts within emerging agentic time-series systems. However, TSFMs exhibi

TouchThinker: Scaling Tactile Commonsense Reasoning to the Open World with Large-scale Data and Action-aware Representation

arXiv:2606.11637v1 Announce Type: new Abstract: Touch is a key modality for embodied agents to understand the physical world. Although recent work has incorporated tactile signals into language system

Toward Generalist Autonomous Research via Hypothesis-Tree Refinement

arXiv:2606.11926v1 Announce Type: cross Abstract: Scientific progress depends on a repeated loop of exploration, experimentation, and abstraction. Researchers test candidate directions, interpret the

Toward Trustworthy AI: Multi-Target Adversarial Attacks and Robust Defenses for Continuous Data Summarization

arXiv:2606.11804v1 Announce Type: new Abstract: Trustworthy AI requires reliable data-processing pipelines, not only robust downstream predictive models. As an upstream component, data summarization d

Towards Data-free and Training-free Compression for Speech Foundation Models Using Parameter Clustering

arXiv:2606.11836v1 Announce Type: cross Abstract: This paper presents a novel data-free and training-free compression approach for speech foundation models using channelwise clustering via k-means. Mo

Towards Fully Automated Exam Grading: Fairness-Aware Recognition of Handwritten Answers with Foundation Models

arXiv:2606.11477v1 Announce Type: cross Abstract: Correcting handwritten exams by hand is time-consuming and error-prone, particularly for large cohorts, while fully digital exams tend to force a dida

Up until yesterday, our entire MTS team has operated under the philosophy of tokenmaxxing as much as possible on Claude Max plans. With Fabl…

model-releasesjerry-liu--x

Up until yesterday, our entire MTS team has operated under the philosophy of tokenmaxxing as much as possible on Claude Max plans. With Fable, this may no longer be possible: - One of our team members

Using Explainability as a Training-Time Reliability Signal for Efficient ECG Classification

arXiv:2606.12252v1 Announce Type: cross Abstract: Training deep neural networks for clinical time-series analysis is computationally demanding, yet many healthcare settings lack the resources required