All entries

Text2GraphQuery-Bench: A Text to Graph Query Benchmark

arXiv:2602.11745v2 Announce Type: replace Abstract: Graph models are fundamental to data analysis in domains rich with complex relationships. Unlike SQL, which benefits from a rel- atively unified sta

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale

DGX agent

arXiv:2608.04355v1 Announce Type: new Abstract: Accuracy changes after language-model self-revision are usually interpreted as changes in reasoning. We show this can fail at the answer-extraction boun

model-releasesarxiv-cs-cl

6 Aug 2026

The Cost of Binarizing Survival Outcomes in Clinical Prognostic Modeling

arXiv:2608.04046v1 Announce Type: cross Abstract: Survival analysis is an established framework for analyzing time-to-event data, yet many clinical machine learning studies still binarize the outcome

researcharxiv-cs-lg

The death of SLMs?

model-releasesr-localllama

I love to see these impressive models coming out that compete with the giants from companies like Z.ai, Moonshot, Alibaba, etc. A win for the open source/weight community is always welcome. While I am

The Effect of Perceived Race and Gender on Police Language Use: Experimental Evidence from VR Simulations

arXiv:2608.05050v1 Announce Type: cross Abstract: Against the backdrop of violence in police interactions with the U.S. public, we explore how deferentially police officers speak to virtual characters

researcharxiv-cs-ai

The Evaluator Is Part of the Experiment: Measuring Open-Ended LLM Conformity

arXiv:2608.04463v1 Announce Type: new Abstract: Prior work on LLM conformity largely measures discrete answer flips under verifiable labels. Open-ended revisions require a different measurement strate

The Fairness Collapse Phenomenon: Bias Amplification in Language Models Trained on Synthetic Data

arXiv:2608.04268v1 Announce Type: new Abstract: Generative models trained on artificially generated data have been shown to exhibit model collapse, resulting in significant performance degradation. As

safetyarxiv-cs-cl

The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question Answering

arXiv:2608.04589v1 Announce Type: cross Abstract: EgoCross is a cross-domain egocentric video question answering benchmark designed to evaluate whether multimodal large language models can generalize

The LLM Proposes, the Executive Disposes: A Self-Verifying Agent Instrument that Dissociates Commitment Drift from Binding Drift in Long-Horizon Agents

arXiv:2608.04066v1 Announce Type: new Abstract: How do you verify a long-horizon agent when its own state and self-reports are exactly what you cannot trust? We present an agent instrument built so th

agentsarxiv-cs-ai

The Loss Does Not See the Basis, but Adam Does

model-releasesarxiv-cs-lg

arXiv:2608.05136v1 Announce Type: new Abstract: Gradient descent on a factored model W = UV^op is implicitly biased toward low-rank solutions, while Adam, starting from the same small initialization,

Local Ai

The Neural Echo: A Signal Processing Perspective for Understanding Neural Networks

arXiv:2608.04864v1 Announce Type: cross Abstract: We introduce the neural echo as a tool for understanding the behavior of neural networks. It generalizes the model-based concepts of impulse responses

local-aiarxiv-cs-lg

The new GPT-5.6 Sol powers all chats for paid users, including Instant, creating one consistent experience. In our high-stakes factuality ev…

The new GPT-5.6 Sol powers all chats for paid users, including Instant, creating one consistent experience. In our high-stakes factuality evaluation covering finance, medicine and law, the new GPT‑5.6

model-releasesopenai--x

The Order Is the Guarantee: Verifier-Budgeted Code Deletion with Static-First Learned Proposals

arXiv:2608.04611v1 Announce Type: cross Abstract: Frontier coding models now match or exceed strong human reference points on programming benchmarks, yet benchmark success does not imply maintainable

The Personalization Mirage: How LLMs Fabricate User Profiles, and Why Self-Monitoring Misleads

arXiv:2608.04570v1 Announce Type: new Abstract: Personalized LLMs with persistent memory are increasingly deployed, yet the faithfulness of their user models remains unexamined. We study over-inferenc

researcharxiv-cs-cl

Applications

The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing

arXiv:2608.04432v1 Announce Type: cross Abstract: On two-sided content platforms, symmetric two-sided isolation (assigning matched fractions of creators and viewers to isolated treatment and control s

applicationsarxiv-cs-lg

Tutorials

The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning

arXiv:2608.04285v1 Announce Type: new Abstract: Neurosymbolic AI systems that integrate machine learning and symbolic reasoning are rapidly gaining attention. They complement the data-intensive statis

tutorialsarxiv-cs-ai

The Sample Complexity of Distributionally Robust PAC Learning under Cressie--Read Divergences

arXiv:2608.04686v1 Announce Type: new Abstract: We study distributionally robust PAC learning for the 0--1-loss, where adversarial perturbations of the data distribution are constrained by a Cressie--

researcharxiv-cs-lg

the smartest young people in sf were working on agi/alignment 5-10y ago. they are working on bci today. naomi is a total star and is one of …

the smartest young people in sf were working on agi/alignment 5-10y ago. they are working on bci today. naomi is a total star and is one of an explosion of young talent into the bci space recently. i’

safetysonya-huang--x

The Yokai Learning Environment: Tracking Beliefs Over Space and Time

arXiv:2508.12480v3 Announce Type: replace Abstract: The ability to cooperate with unknown partners is a central challenge in cooperative AI and widely studied in the form of zero-shot coordination (ZS

They almost catched up on Frontier performance, so now catching up on prices

model-releasesr-localllama

Users also report that the free version was significantly downgraded after the release of the new models this is very important for us when considering local hosting. A lot of people decided not to bu

Thinking with Anchors: Grounded and Efficient Document Reasoning

model-releasesarxiv-cs-cv

arXiv:2608.04424v1 Announce Type: new Abstract: Existing document understanding benchmarks have largely focused on locating page elements, yet real-world document intelligence requires models to reaso

Applications

This definitely seems like something worth noting, and illustrates the gap between Fable/Astra class models and the previous frontier that w…

applicationsethan-mollick--x

This definitely seems like something worth noting, and illustrates the gap between Fable/Astra class models and the previous frontier that was 'merely' good at hacking under human instructions. Initia

This paper by researchers from MIT and Stanford finds that most people would be financially better off if they followed the financial advice…

model-releasesethan-mollick--x

This paper by researchers from MIT and Stanford finds that most people would be financially better off if they followed the financial advice of LLMs (GPT-5.2 & Gemini 3 Flash) But some people get a bi

This webinar is happening in 30 minutes, and that means there's still time to register! Following the discussion will be an open Q&A with ou…

model-releasesfireworks-ai--x

This webinar is happening in 30 minutes, and that means there's still time to register! Following the discussion will be an open Q&A with our Head of AI Education @Prof_OZ, and the @arizeai team. See

TIDE: A Physically Diverse 3D Turbulence Benchmark Dataset for Advancing Scientific Machine Learning

model-releasesarxiv-cs-lg

arXiv:2608.04222v1 Announce Type: cross Abstract: Turbulence is a central testbed for machine learning on physical dynamics because its governing laws are known exactly. However, most existing studies

Applications

Together Serverless Inference gives developers a managed production path for bringing FLUX 3 into creative products and automated media work…

applicationstogether-ai--x

Together Serverless Inference gives developers a managed production path for bringing FLUX 3 into creative products and automated media workflows. Start building: https://www.together.ai/models/flux-3

ToolArtist: Tool-Using Unified Multimodal Models for Agentic Image Generation

arXiv:2608.04436v1 Announce Type: new Abstract: Text-to-image (T2I) models can produce visually compelling images, yet they remain limited on open-world tasks that require complex semantic understandi

safetyarxiv-cs-cv

TopoChunker: Topology-Aware Agentic Document Chunking Framework

arXiv:2603.18409v2 Announce Type: replace Abstract: Current document chunking methods for Retrieval-Augmented Generation (RAG) typically linearize text. This forced linearization strips away intrinsic

agentsarxiv-cs-cl

TourSynbio-Search: A Large Language Model Driven Agent Framework for Unified Search Method for Protein Engineering

arXiv:2411.06024v1 Announce Type: cross Abstract: The exponential growth in protein-related databases and scientific literature, combined with increasing demands for efficient biological information r

agentsarxiv-cs-ai

Toward Federated Large Language Models in Medicine: A Parameter-Efficient Framework for Privacy-Preserving, Multi-Institutional Adaptation

arXiv:2601.22124v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly adapted for medical applications, but most are trained using data from a single institution because pr

Toward Integrating Adaptive Experience Replay and Online Uncertainty Estimation in Safe Actor-Critic Optimal Control

arXiv:2608.04732v1 Announce Type: cross Abstract: Safe actor-critic control often treats barrier filtering, uncertainty estimation, and experience replay as separate modules, even though each changes

Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning

arXiv:2608.05139v1 Announce Type: new Abstract: Long-horizon reasoning in recent LLMs demands that the model switch between distinct skills inside a reasoning chain, such as first doing a math derivat

Towards a New Grammar of Reasoning for Artificial Legal Intelligence and the Mecelle as Its Semantic Protocol

arXiv:2608.04011v1 Announce Type: cross Abstract: This article examines the enduring epistemic and methodological crisis of traditional legal practice in light of the opportunities and constraints int

agentsarxiv-cs-ai

Towards a satellite image manipulation and deepfake localization benchmark dataset

arXiv:2608.04840v1 Announce Type: cross Abstract: Verifying the authenticity of satellite imagery has become increasingly critical given advances in generative artificial intelligence. Highly realisti

Towards End-to-End Multilingual Metaphor Processing: Integrating Detection, Translation, and Evaluation

arXiv:2608.04260v1 Announce Type: new Abstract: Metaphorical language remains a major challenge for multilingual natural language processing because successful interpretation and translation require r

researcharxiv-cs-cl

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes

arXiv:2608.05000v1 Announce Type: new Abstract: Vision offers a critical axis for advancing foundation models, driving a shift towards natively unified multimodal pretraining. Despite this momentum, t

safetyarxiv-cs-cv

Towards Trustworthy Hypergraph Neural Networks under Label Noise

arXiv:2608.04377v1 Announce Type: cross Abstract: Hypergraph neural networks (HGNNs) have demonstrated remarkable capabilities in processing complex higher-order relationships. However, their performa

Towards Understanding Gradient Flow Dynamics of Homogeneous Neural Networks Beyond the Origin

arXiv:2502.15952v3 Announce Type: replace Abstract: Recent works exploring the training dynamics of homogeneous neural network weights under gradient flow with small initialization have established th

researcharxiv-cs-lg

Towards Valid B-Rep Generation: Training-Free Wireframe Anomaly Detection and Repair

arXiv:2608.04955v1 Announce Type: new Abstract: Multi-stage boundary representation (B-Rep) generation leverages intermediate wireframes to synthesize CAD models. However, geometric and topological ri

researcharxiv-cs-cv

Local Ai

Trace, Verify, and Correct: A Training-Free Framework for Spatial Reasoning in Multimodal LLMs

arXiv:2608.04759v1 Announce Type: cross Abstract: Although Multimodal Large Language Models (MLLMs) have made substantial progress, their spatial reasoning may still produce intermediate judgments inc

local-aiarxiv-cs-cl

Traceable LLM-Generated Hazard Scenarios for Operational Safety Analysis of Aviation Systems Using ASRS Reports

arXiv:2608.04697v1 Announce Type: new Abstract: Operational hazard analysis of aviation system operations must consider interactions among weather, ATC actions, airspace constraints, aircraft operatio

safetyarxiv-cs-ai

Training Crossroads for Recurrent Vision Transformers: Recurrence, Neural ODEs, and Deep Supervision

model-releasesarxiv-cs-cv

arXiv:2608.04879v1 Announce Type: cross Abstract: Vision Transformers (ViTs) achieve strong image-recognition performance, but their parameter count grows linearly with depth when each block is indepe

Local Ai

Training-Free Hashing-Based Attention via Binary Principal Components

arXiv:2608.04405v1 Announce Type: cross Abstract: Long-context large language models (LLMs) are increasingly deployed in real-world applications, yet self-attention remains a major efficiency bottlene

local-aiarxiv-cs-ai

Transfer Learning for Named Entity Recognition of Classical Latin through LLM Prompting

arXiv:2608.04015v1 Announce Type: new Abstract: With the increase in digitized resources of Classical Latin texts and modern breakthroughs of Large Language Models (LLMs), I contribute to ancient lang

Transferable Dual-Stream Representations for Mesoscale-Preserving Sea Surface Temperature Downscaling

arXiv:2608.04230v1 Announce Type: cross Abstract: Deep learning models for scientific spatio-temporal downscaling often minimize reconstruction error while failing to preserve physically meaningful mu

researcharxiv-cs-cv

TRCoRSurg: Temporal-Relational Co-Reasoning for Surgical Video Triplet Recognition

arXiv:2608.04606v1 Announce Type: new Abstract: Understanding complex surgical scenes requires recognizing multiple interdependent entities, such as instruments, actions, and targets, while maintainin

researcharxiv-cs-cv

TriCLE: Tri-Modal Vision-Language Reasoning for Edge-Deployed Fine-Grained Clustering

arXiv:2608.04175v1 Announce Type: new Abstract: Edge platforms used for aerial observation must interpret aircraft imagery under limited memory, limited compute, and intermittent connectivity. This se

safetyarxiv-cs-cv

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)

arXiv:2608.04317v1 Announce Type: cross Abstract: Autonomous cyber defense systems based on Deep Reinforcement Learning (DRL) have attracted significant research attention, yet remain evaluated almost