Search: “models”

From Correctness to Utility: Gain-Based Prefix Evaluation for LLM Reasoning

arXiv:2606.07190v1 Announce Type: new Abstract: Reasoning prefixes shape the future trajectory of LLM problem solving, yet existing process reward models usually evaluate them through local step corre

local-aiarxiv-cs-cl

Model Releases

HKJudge: A Legal Discourse-Annotated Corpus for Interpreting What Courts Find, How They Reason, and What They Rule

DGX agent

arXiv:2606.06679v1 Announce Type: cross Abstract: Court judgments are central to legal practice and jurisprudence, yet discourse analysis of Hong Kong judgments has received limited attention, owing l

model-releasesarxiv-cs-ai

8 Jun 2026

How reliable are LLMs when it comes to playing dice?

arXiv:2606.07515v1 Announce Type: cross Abstract: We investigate the probabilistic reasoning capabilities of large language models through a controlled benchmarking study on discrete probability probl

safetyarxiv-cs-ai

HybridCodec: Fast Dual-Stream, Semantically Enhanced Neural Audio Codec

arXiv:2606.06743v1 Announce Type: cross Abstract: The popularity of neural audio codecs as speech tokenizers has surged with the advent of Multimodal Large Language Models. New codec architectures wit

MMAE: A Massive Multitask Audio Editing Benchmark

arXiv:2606.07229v1 Announce Type: cross Abstract: We introduce MMAE, a Massive Multitask Audio Editing benchmark, serving as the first comprehensive evaluation testbed designed for general-purpose ins

Never Seen Before: Benchmarking Genuine Zero-Shot Composed Image Retrieval with Consistent Video-Sourced Datasets

arXiv:2606.07032v1 Announce Type: cross Abstract: Zero-Shot Composed Image Retrieval (ZS-CIR) aims to retrieve a target image based on a query composed of a reference image and a relative caption with

Oh my God! @METR_Evals’s coding benchmarks are saturated! 🤯 Mythos broke the METR graph 🤯 4 weeks later, out comes a new coding task, this…

model-releasesgary-marcus--x

Oh my God! @METR_Evals’s coding benchmarks are saturated! 🤯 Mythos broke the METR graph 🤯 4 weeks later, out comes a new coding task, this time from @cognition: “FrontierCode Diamond remains unsaturat

Tutorials

On the importance of multiple training seeds for evaluating machine unlearning

arXiv:2510.26714v5 Announce Type: replace-cross Abstract: Machine unlearning aims to remove the influence of certain data points from a trained model without costly retraining. Most practical unlearni

tutorialsarxiv-cs-ai

Queen-Bee Agents: A BeeSpec-Centered Architecture for Governed Enterprise MCP Orchestration

arXiv:2606.06545v1 Announce Type: cross Abstract: Enterprise agent systems increasingly need to connect large language models to private tools, internal knowledge, and Model Context Protocol (MCP) int

local-aiarxiv-cs-ai

Style or Content? Evaluating Style Classifiers with Controlled Content Overlap

arXiv:2606.07103v1 Announce Type: new Abstract: Style classifiers can use content cues that correlate with style labels in naturally collected data, yet we lack a systematic way to measure this relian

Supervision versus Demonstration-Based In-Context Learning for Multiword Expression Classification

arXiv:2606.07479v1 Announce Type: cross Abstract: Turkish idiomatic light verb constructions (LVCs) are challenging for multiword expression processing because they often share the same surface form a

SVHighlights: Towards Extremely Long Sport Video Highlight Detection

arXiv:2606.06926v1 Announce Type: new Abstract: While highlight detection for long-form videos is of great practical importance, most existing methods remain limited to short-form content, largely due

'Testing LCM on a GTX 750 Ti 4GB: Surprisingly Usable for Low-VRAM AI Image Generation'

local-air-stablediffusion

This post documents testing Latent Consistency Models (LCM) on a GTX 750 Ti graphics card with 4GB of VRAM, demonstrating that this older, lower-end GPU can still run AI image generation models with a

The Geography of Algorithmic Judgment: LLM Intermediaries, Place Identity, and Racial Steering in Housing Search

arXiv:2606.06694v1 Announce Type: cross Abstract: Large language models (LLMs) are rapidly assuming an intermediary role in housing search through the integration of listing platforms within conversat

local-aiarxiv-cs-ai

The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook

arXiv:2604.02029v2 Announce Type: replace Abstract: Latent space is rapidly emerging as a native substrate for language-based models. While modern systems are still commonly understood through explici

Think Like a Pilot: Fine-Grained Long-Horizon UAV Navigation

arXiv:2606.06836v1 Announce Type: cross Abstract: Language-guided UAV agents must execute long-horizon semantic instructions while producing smooth, physically feasible continuous flight commands, yet

Tutorials

Trio: Learning Time-Series Forecasting with Temporal-Spatial-Sample Attention and Structural Causal Priors

arXiv:2606.07291v1 Announce Type: new Abstract: Multivariate time-series forecasting requires models to reason over temporal dynamics, cross-variable dependencies, and historical input-output correspo

tutorialsarxiv-cs-lg

TSAQA: Time Series Analysis Question And Answering Benchmark

arXiv:2601.23204v2 Announce Type: replace Abstract: Time series data are integral to critical applications across domains such as finance, healthcare, transportation, and environmental science. While

Which Anatomy Matters Under Limited Labels? A Data-Efficient Anatomy-Aware Benchmark for Cardiac Pathology Prediction

arXiv:2606.06509v1 Announce Type: cross Abstract: Numerous medical imaging problems must be solved under limited labels and constrained compute, yet it remains unclear whether performance gains are dr

Agents

2-Step Agent: A Framework for the Interaction of a Decision Maker with AI Decision Support

arXiv:2602.21889v2 Announce Type: replace Abstract: Predictions from ML models support human decision making in several fields, including high-stakes ones such as healthcare and the judiciary. Yet, we

agentsarxiv-cs-ai

b9544

local-aillama-cpp-releases

B9544 is an intermediate build release of llama.cpp, an open-source C/C++ library for running large language model inference. Llama.cpp uses the GGUF model format and supports multiple hardware backen

Benchmark Everything Everywhere All at Once

arXiv:2606.06462v1 Announce Type: new Abstract: Benchmarks are fundamental for evaluating and advancing LLMs and MLLMs by providing standardized and explicit measures of performance. However, their co

Ideogram 4 on comfyui

local-air-stablediffusion

Ideogram 4.0 is an open-weights 9.3B parameter text-to-image model that received native support in ComfyUI on day zero of its release. The model excels at generating posters, layouts, and readable cop

Tutorials

Level Up: Defining and Exploiting Transitional Problems for Curriculum Learning

arXiv:2603.13761v2 Announce Type: replace-cross Abstract: Curriculum learning--ordering training examples in a sequence to aid machine learning--takes inspiration from human learning, but has not gain

tutorialsarxiv-cs-ai

Hardware

LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

arXiv:2603.19312v3 Announce Type: replace-cross Abstract: Joint Embedding Predictive Architectures (JEPAs) offer a compelling framework for learning world models in compact latent spaces, yet existing

hardwarearxiv-cs-ai

Metamorphic Testing with the Rashomon Set: Explanation Faithfulness in Machine Learning

arXiv:2606.06056v1 Announce Type: cross Abstract: Multiple machine learning models can achieve near-equivalent predictive performance on the same task, yet provide divergent feature-based explanations

Agents

Microskill Architecture: A Modular Skill-Driven Framework for AI-Native Code Generation

arXiv:2606.05720v1 Announce Type: cross Abstract: Large language models and AI coding agents have reshaped software development, but the path to fully AI-native systems faces structural challenges. Ch

agentsarxiv-cs-ai

Ouch.

Ouch. > be Sam Altman > see internally that ARR numbers are brutally contracting bc tokenmaxxing era is over + cheaper models are closing the gap on frontier models + LLMs are plateauing and becoming

safetygary-marcus--x

Running Python code in a sandbox with MicroPython and WASM

model-releasessimon-willison

I've been experimenting with different approaches to running code in a sandbox for several years now, but my latest attempt feels like it might finally have all of the characteristics I've been lookin

Separation Power of Equivariant Neural Networks

arXiv:2406.08966v3 Announce Type: replace-cross Abstract: The separation power of a machine learning model refers to its ability to distinguish between different inputs and is often used as a proxy fo

TAPO: Tool-Aware Policy Optimization via Credit Transfer for Multimodal Search Agents

arXiv:2606.05784v1 Announce Type: new Abstract: We identify and formally characterize credit misassignment as a systematic failure mode of GRPO in tool-augmented multimodal search agents: its uniform

The End of Software Engineering: How AI Agents Are Fundamentally Restructuring the Software Paradigm

arXiv:2606.05608v1 Announce Type: cross Abstract: For over half a century, software engineering has operated on a foundational premise: human engineers decompose problems, encode decision logic into s

Where Should Knowledge Enter? A Layered Framework for Knowledge Infusion in Multimodal Iterative Generative Mo

arXiv:2606.06356v1 Announce Type: new Abstract: Multimodal generative models produce fluent outputs but remain unreliable when generation must respect structured, domain-specific, or safety-critical k

safetyarxiv-cs-ai

A Novel Method with Encoder-Decoder for Cross-Sensor Adaptation in Surface Shape Sensing with Sparse Strain Sensors

model-releasesarxiv-cs-ro

arXiv:2606.05903v1 Announce Type: new Abstract: Performance variations in sensor arrays, caused by intrinsic differences or installation conditions, can lead to inconsistent results during shape sensi

Agents

ABBEL: Learning Natural-Language Belief States for Memory-Efficient Interaction

arXiv:2512.20111v2 Announce Type: replace Abstract: As the time horizons of sequential decision-making tasks grow, keeping full interaction histories in model context becomes increasingly costly. Rece

agentsarxiv-cs-cl

Better Literary Translation: A Multi-Aspect Data Generation and LLM Training Approach

arXiv:2606.05924v1 Announce Type: new Abstract: Literary translation poses unique challenges due to the scarcity of high-quality annotated data and the need to balance expression fluency with literary

CLFEC: A New Task for Unified Linguistic and Factual Error Correction in paragraph-level Chinese Professional Writing

arXiv:2602.23845v2 Announce Type: replace Abstract: Chinese text correction has traditionally focused on spelling and grammar, while factual error correction is usually treated separately. However, in

Complexity-Balanced Diffusion Splitting

arXiv:2606.06477v1 Announce Type: new Abstract: Standard continuous-time generative models rely on monolithic architectures that must navigate vastly different signal regimes, from isotropic noise to

local-aiarxiv-cs-cv

Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments

arXiv:2606.05661v1 Announce Type: cross Abstract: Continual learning, the ability of AI systems to improve through sequential experience, has attracted substantial interest, but no high-quality benchm

Do MLLMs Capture How Interfaces Guide User Behavior? A Benchmark for Multimodal UI/UX Design Understanding

arXiv:2505.05026v5 Announce Type: replace Abstract: User interface (UI) design goes beyond visuals to shape user experience (UX), underscoring the shift toward UI/UX as a unified concept. While recent

EgoAdapt: A Multi-Scene Egocentric Adaptation Method for CVPR 2026 HD-EPIC VQA Challenge

arXiv:2605.24500v2 Announce Type: replace Abstract: This technical report presents our solution, EgoAdapt (Egocentric Adaptation via Category, Calibration, and Consistency), to the CVPR 2026 HD-EPIC V

English-to-Prakrit Machine Translation via Multilingual Transfer Learning

arXiv:2606.06038v1 Announce Type: new Abstract: We study English-to-Prakrit machine translation in a low-resource setting where the target language is unsupported by IndicTrans2. We adapt the multilin

FATE: Focal-modulated Attention Encoder for Multivariate Time-series Forecasting

arXiv:2408.11336v3 Announce Type: replace-cross Abstract: Climate change stands as one of the most pressing global challenges of the twenty-first century, with far-reaching consequences such as rising

FiLM-Based Speaker Conditioning of a SpeechLLM for Pathological Speech Recognition

arXiv:2606.06211v1 Announce Type: new Abstract: Automatic speech recognition (ASR) has advanced remarkably for standard speech; however, pathological speech from neurological conditions remains a sign

GRAMformer: Any-Order Modality Interactions via Volumetric Multimodal Cross-Attention

arXiv:2606.06249v1 Announce Type: new Abstract: Transformer-based multimodal models rely on attention mechanisms to integrate information across heterogeneous modalities. Despite their success, existi

researcharxiv-cs-cv

Tools

@ideogram_ai Ideogram 4 is now available on Together AI. Try it now: http://www.together.ai/models/ideogram-40

Ideogram 4, an AI image generation model, has been made available on the Together AI platform. Users can now access and experiment with Ideogram 4 through Together AI's model interface at together.ai/

toolstogether-ai--x

Is This Edit Correct? A Multi-Dimensional Benchmark for Reasoning-Aware Image Editing

arXiv:2606.05172v1 Announce Type: cross Abstract: Diffusion-based image editing has achieved strong visual fidelity under natural language instructions, yet most existing systems still operate at the

Learning Visual Spatial Planning from Symbolic State via Modality-Gap-Aware Self-Distillation

arXiv:2606.06076v1 Announce Type: cross Abstract: While vision-language models excel at general multimodal understanding, they still struggle with visual spatial planning. We attribute this to a perce

safetyarxiv-cs-cv