Search: “models”

Recovering Lesion Parameters from Aphasic Picture Naming Error Profiles in Large Language Models

arXiv:2608.06429v1 Announce Type: new Abstract: Interpretability methods for large language models (LLMs) describe internal state but do not directly test whether that state is causally sufficient to

researcharxiv-cs-cl

10 Aug 2026

Agents

the term “RLM” (recursive language model) got a lot of buzz this week, but this idea is not new! @a1zhang wrote the og RLM paper 10 months a…

DGX agent

the term “RLM” (recursive language model) got a lot of buzz this week, but this idea is not new! @a1zhang wrote the og RLM paper 10 months ago! thats like 5 agent-years! would highly recommend followi

agentsharrison-chase--x

9 Aug 2026

Kimi K3 (Unsloth) IQ2-XXS from 711GB down to 478GB!!! Only Multi-language was removed to trim the size

model-releasesr-localllama

Firstly a big thanks to the poster 'hellohazine', he basically only removed the multi-lingual fat of the model and just kept the English language intact. It is the exact model, and the rest of the mod

8 Aug 2026

A note on conditional PAC-efficient reasoning in large language model routing

arXiv:2512.03057v2 Announce Type: replace-cross Abstract: We study distribution-free risk control for model routing, motivated by large language model reasoning. We formalize pointwise conditional eff

Bayesian Expected Uncertainty Reduction (B-EUR) Model: A Computational Account of What Makes Design Options Worth Trying

arXiv:2608.05642v1 Announce Type: new Abstract: This paper proposes the Bayesian Expected Uncertainty Reduction (B-EUR) model, which formalizes the value of trying a candidate design action as its exp

CPC-CMS: Cognitive Pairwise Comparison Classification Model Selection Framework for Document-level Sentiment Analysis

arXiv:2507.14022v2 Announce Type: replace Abstract: This study proposes the Cognitive Pairwise Comparison Classification Model Selection (CPC-CMS) framework for document-level sentiment analysis. The

researcharxiv-cs-cl

CREBench: Evaluating Large Language Models in Cryptographic Binary Reverse Engineering

arXiv:2604.03750v2 Announce Type: replace-cross Abstract: Reverse engineering (RE) is central to software security, particularly for cryptographic programs that handle sensitive data and are highly pr

Faster and Better Alignment for Flow Matching Models via Step-aware Advantages

arXiv:2602.01591v2 Announce Type: replace Abstract: Recent advances in flow matching models, particularly with reinforcement learning (RL), have significantly enhanced human preference alignment in fe

safetyarxiv-cs-cv

Grounded Well-Condition Anomaly Detection on the Volve Field: Constructed Labels, a Baseline, and a Dual-Head Model

arXiv:2608.05685v1 Announce Type: new Abstract: Most public benchmarks for machine-condition monitoring come from test rigs, where faults are induced on purpose and every event is known. Real producti

Applications

Marginal Matching Does Not License Factorized Sampling: Auditing Conditional Style Leakage in Factorized Generative Models

arXiv:2608.05243v1 Announce Type: cross Abstract: Factorized generative models commonly regularize a latent style variable z_s by matching its marginal distribution to a fixed Gaussian prior and inter

applicationsarxiv-cs-ai

Applications

Persona-Pruner: Sculpting Lightweight Models for Role-Playing

arXiv:2606.14695v2 Announce Type: replace-cross Abstract: Language Models (LMs) have shown remarkable potential as role-playing chatbots, delivering consistent, stylized interactions when given a spec

applicationsarxiv-cs-cl

Tutorials

Quantum-Structured World Models (QSWMs) for Predictive Latent Dynamics

arXiv:2608.05371v1 Announce Type: new Abstract: World models learn latent states that summarize interaction histories, evolve over time, and support prediction, simulation, or planning. Most existing

tutorialsarxiv-cs-lg

Robust-WAM: Bridging Generative Pretraining and Semantic Foresight in World-Action Models

arXiv:2608.05903v1 Announce Type: new Abstract: Mainstream World-Action Models (WAMs) adapt pretrained video generation models (VGMs) for robot control, transferring their learned dynamics prior for a

safetyarxiv-cs-cv

SkillTFM: Gated Skill Evolution for Training-Free Adaptation of Tabular Foundation Models

model-releasesarxiv-cs-lg

arXiv:2608.06137v1 Announce Type: new Abstract: Tabular data are ubiquitous in real-world applications and are crucial for data-driven prediction and decision-making across science, industry, finance,

Text-Guided Refinement of Multi-sequence Glioma Subregion Segmentation with a Vision-Language Foundation Model

arXiv:2608.05389v1 Announce Type: new Abstract: Background: Accurate glioma subregion delineation is important for radiotherapy planning and longitudinal monitoring, but manual contour correction is t

The Ignition Index: Measuring Global Workspace Dynamics in Language Models

arXiv:2608.05160v1 Announce Type: new Abstract: We introduce the Ignition Index (I), a validated scalar metric that operationalizes Global Workspace Theory's (GWT) all-or-none ignition prediction in t

World-to-Wrist: Task-Conditioned Future Wrist Modeling for Fine-Grained Robot Manipulation

arXiv:2608.05369v1 Announce Type: cross Abstract: Vision-language-action (VLA) models often treat main-view and wrist-view observations as parallel visual inputs, overlooking their distinct roles in r

local-aiarxiv-cs-cv

Best open-source harnesses for combining cloud and local AI model orchestration?

Looking for best current solutions for combining cloud models and local models seamlessly inside a harness' orchestration Edit: Right now, we don't have harnesses (that I'm aware of) that are blending

local-air-localllama

Chained Recursive Language Models for Multi-Iteration Reasoning

arXiv:2608.05124v1 Announce Type: cross Abstract: Long context reasoning in large language models (LLMs) is usually constrained by the fact that a single inference trajectory has to simultaneously exp

EdgeLM: Edge Demonstrations for Language Models' Table Understanding

arXiv:2608.04390v1 Announce Type: new Abstract: Large language models (LLMs) perform table-centric prediction through in-context learning, making demonstration selection critical to performance. Exist

researcharxiv-cs-cl

Filing: DeepSeek has invested ~$20.8M in Unitree Robotics' Shanghai IPO and agreed to jointly develop AI models for humanoid machines (Eduardo Baptista/Reuters)

Eduardo Baptista / Reuters: Filing: DeepSeek has invested ~20.8M in Unitree Robotics' Shanghai IPO and agreed to jointly develop AI models for humanoid machines — Chinese artificial intelligence start

model-releasestechmeme

Applications

It is past time to take AI & security seriously at the individual level as well. If its not the current OpenAI and Anthropic models doing it…

applicationsethan-mollick--x

It is past time to take AI & security seriously at the individual level as well. If its not the current OpenAI and Anthropic models doing it, then the coming open weights models will when they catch u

Large Language Models for Low-Resource Languages: A Conceptual Framework for an Electronic Explanatory Dictionary of the Tajik Language

model-releasesarxiv-cs-cl

arXiv:2608.04186v1 Announce Type: new Abstract: This paper presents a conceptual framework for developing an electronic explanatory dictionary of the Tajik language using large language models (LLMs).

MERaLiON-GR: Speech Gender Recognition Model for English and SEA Languages

arXiv:2608.04433v1 Announce Type: cross Abstract: We present MERaLiON-GR, a speech gender recognition system that performs binary classification (female / male) on English and Southeast Asian (SEA) la

MobileWAM: Bridging World Action Models to Mobile Manipulation with Chain-of-Foresight

arXiv:2608.04657v1 Announce Type: new Abstract: World action models (WAMs) built on video generation backbones are a rising recipe for robot learning, yet remain confined to tabletop manipulation. Mob

MultiPathFormer: Towards a Foundation Model for Multipath Wireless Propagation

arXiv:2608.05076v1 Announce Type: cross Abstract: Recent advances in machine learning have enabled training of wireless foundation models, which aim to support tasks such as channel estimation, beam p

local-aiarxiv-cs-ai

OpenAI updates the default model for free users to GPT-5.6 Luna, adds unlimited text chats for free users, rolls out an improved GPT-5.6 Sol version, and more (Herb Scribner/Axios)

Herb Scribner / Axios: OpenAI updates the default model for free users to GPT-5.6 Luna, adds unlimited text chats for free users, rolls out an improved GPT-5.6 Sol version, and more — OpenAI on Thursd

model-releasestechmeme

Overcoming Statistical Bias in Action-Controllable World Models

arXiv:2608.04653v1 Announce Type: new Abstract: Action-conditioned world models aim to predict how visual environments evolve under an agent's actions. Yet future frames are often highly predictable f

safetyarxiv-cs-cv

Persistent Object Narratives for Token-Efficient Video Language Models

arXiv:2608.04866v1 Announce Type: new Abstract: Video large language models (Video-LLMs) have made strong progress in open-ended video understanding. However, their visual interfaces remain token-inte

Personalized Federated Sparse Adaptation of Time-Series Foundation Models

arXiv:2608.04695v1 Announce Type: cross Abstract: Federated adaptation of time-series foundation models (TSFMs) is attractive for building energy forecasting because meter data are private, distribute

Tutorials

Unforgettable Generalization in Language Models

arXiv:2409.02228v2 Announce Type: replace-cross Abstract: When language models (LMs) are trained to forget (or 'unlearn'') a skill, how precisely does their behavior change? We study the behavior of t

tutorialsarxiv-cs-cl

Adaptive Two-Stage Visual Token Pruning for Efficient Inference in Video-Language Models

arXiv:2608.03112v1 Announce Type: cross Abstract: Vision-language models excel at image and video understanding but suffer from high inference latency due to the need to process thousands of tokens pe

Anthropic confirms it is building an in-house silicon team to design custom chips for Claude, co-designing hardware and models and using a 'multi-chip approach' (Tom Carter/Business Insider)

Tom Carter / Business Insider: Anthropic confirms it is building an in-house silicon team to design custom chips for Claude, co-designing hardware and models and using a “multi-chip approach” — - Anth

model-releasestechmeme

Assessment of Conditional Diffusion Model for Synthetic Histopathology Image Generation

model-releasesarxiv-cs-lg

arXiv:2608.03990v1 Announce Type: new Abstract: Synthetic histopathology image generation has emerged as an approach that may address data scarcity in computational pathology, yet current evaluation m

BanglaWild: An In-the-Wild Bengali Scene Text Recognition Benchmark for OCR and Vision-Language Models

model-releasesarxiv-cs-cl

arXiv:2608.03884v1 Announce Type: cross Abstract: In-the-wild Bengali scene text recognition is largely unmeasured: existing resources target handwritten documents or constrained sign-board parsing, r

CorePath: A Breast-Specialized Pathology Foundation Model for Core Needle Biopsy Diagnosis and Risk-Controlled Report Generation

arXiv:2608.03079v1 Announce Type: cross Abstract: Breast core needle biopsy (CNB) is central to breast cancer diagnosis yet remains challenging because limited tissue sampling, lesion heterogeneity, a

Disentangling Language Modeling and Boundaries

arXiv:2608.03599v1 Announce Type: new Abstract: Byte-level language models are usually argued for on the grounds of robustness, multilingual fairness, and character-level skills. We point to a differe

safetyarxiv-cs-cl

Federated generative event models for tokenized electronic health records

arXiv:2608.02939v1 Announce Type: new Abstract: Electronic health record foundation models are limited by institutionally siloed data and substantial performance degradation under cross-site transfer.

researcharxiv-cs-lg

FOUND-AF: Benchmarking ECG Foundation Models for Atrial Fibrillation Detection

arXiv:2608.03597v1 Announce Type: new Abstract: Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia and is associated with increased risks of stroke, heart failure, and mortality.

HUKUKBERT: Domain-Specific Language Model for Turkish Law

model-releasesarxiv-cs-cl

arXiv:2604.04790v2 Announce Type: replace Abstract: Natural language processing (NLP) advances have powered a generation of LegalTech systems, but Turkish law remains under-served by domain-specific d

Interpreting Black-Box Large Language Models with Sentence-Level Energy Landscapes

arXiv:2608.02879v1 Announce Type: new Abstract: The widespread adoption of proprietary Large Language Models (LLMs) accessed strictly through closed APIs has created a critical challenge for responsib

local-aiarxiv-cs-ai

Modeling Long-Term Memory and Temporal Attention Shifts for Video Salient Object Ranking with a New Benchmark

arXiv:2203.17257v2 Announce Type: replace Abstract: Salient Object Ranking (SOR) aims to estimate the relative saliency order among multiple salient objects. While SOR has been extensively studied in

UniNav: A Unified World-Action Diffusion Model for Visual Navigation

arXiv:2608.03244v1 Announce Type: new Abstract: Image-goal visual navigation is a fundamental capability for embodied agents. Existing navigation policies efficiently predict waypoint trajectories but

VIBE: A VAD-Informed Benchmark for Entity-Centered Affective Profiling of Large Language Model Outputs

arXiv:2608.03810v1 Announce Type: cross Abstract: Large language models routinely describe socially salient targets, including political figures, countries, religions, organizations, historical events

All models are currently 20% discounted in Portal, other than GPT-5.6 Terra and Luna which 50% off and DeepSeek V4 Flash 0731 which is 90% o…

model-releasesnous-research--x

All models in the Portal are discounted by 20 %, except GPT‑5.6 Terra and Luna (50 % off) and DeepSeek V4 Flash 0731 (90 % off). The latest Alibaba Qwen release, Qwen3.8‑Max, is now available for Herm

Attention-Steered Vision-Language Models for Sign Language Translation

arXiv:2608.00235v1 Announce Type: new Abstract: Vision-language models (VLMs) have emerged as a powerful framework for multimodal video understanding. However, they remain limited in the sign language

researcharxiv-cs-cv

CopyCat: Improving Fine-Grained Subject Consistency in Subject-to-Image Models within Seconds

arXiv:2608.00674v1 Announce Type: new Abstract: Recent subject-to-image models have achieved impressive progress in personalized image generation, yet they still struggle to preserve fine-grained subj

researcharxiv-cs-cv

Disentangling Visuo-Tactile Foresight: Oracle-Guided Interface Discovery for World Action Models

model-releasesarxiv-cs-ro

arXiv:2608.00547v1 Announce Type: new Abstract: Contact-rich manipulation remains challenging because successful control depends on physical interaction cues that are often weakly observable from visi