Search: “models”

arXiv:2608.18888v1 Announce Type: new Abstract: The rapid advancement of Natural Language Generation (NLG) has made the reliable evaluation of generated text increasingly critical, as these systems, s

applicationsarxiv-cs-cl

Research

BERTilda: Explainable Topic Lifecycle Tracking with Split/Merge Detection via Similarity-and-Flow Temporal Graphs

DGX agent

arXiv:2608.18101v1 Announce Type: new Abstract: Longitudinal text streams exhibit topic birth and death, but also discrete structural reorganizations in which themes split into subtopics or merge into

researcharxiv-cs-cl

20 Aug 2026

CausalProfiler: Generating Synthetic Benchmarks for Rigorous and Transparent Evaluation of Causal Machine Learning

arXiv:2511.22842v3 Announce Type: replace-cross Abstract: Causal machine learning (Causal ML) aims to answer 'what if' questions using machine learning algorithms, making it a promising tool for high-

ComponentBench: Diagnosing Component-Level Failures in Computer-Use Agents

arXiv:2608.18307v1 Announce Type: new Abstract: Current evaluation of computer-use agents is split between long-horizon workflow benchmarks and atomic GUI-grounding tests. This leaves an under-instrum

CTIFoundry: An Agent-Native Corpus Scaffold for Cyber Threat Intelligence

arXiv:2608.18613v1 Announce Type: new Abstract: Cyber threat intelligence (CTI) is increasingly consumed not by human analysts but by LLM agents that compose multi-step investigations at query time. T

Event-Causal RAG: A Retrieval-Augmented Generation Framework for Long Video Reasoning in Complex Scenarios

arXiv:2605.06185v2 Announce Type: replace Abstract: Large vision-language models perform well on short- and medium-length video understanding but still struggle to maintain coherent event memory and r

extsc{TestifAI}: Tomography-Based Testing for Deep Learning Systems

arXiv:2608.18900v1 Announce Type: new Abstract: As AI systems are increasingly deployed in safety-critical application domains (e.g., autonomous driving), associated risks increase too. Deep learning

Fine-tuning Cactus Needle 2 can match DeepSeek v4 on the specific task

Hey LocalLlama, Henry from Cactus here! When we trained Needle 2, I had a strict rule to not expose the model to any data sample that remotely felt like these benchmarks. It seemed over-the-top, but b

Local Ai

Flama: a Python framework for development and deployment of production-ready APIs, machine learning, and LLM services

arXiv:2608.18733v1 Announce Type: cross Abstract: We present Flama, an open-source Python framework for developing and deploying production-ready web APIs, machine learning services, and large-languag

local-aiarxiv-cs-ai

FrenchNews-7: Benchmarking Cross-Publisher French News Editorial Desk Classification

arXiv:2608.18097v1 Announce Type: new Abstract: We present FrenchNews-7, a cross-publisher France-based French-language news editorial desk classification benchmark combining a large multi-outlet corp

How Quantum Is the Advantage? A Fair, Calibration- and Noise-Aware Benchmark and Attribution Audit of Quantum Machine Learning for Network Intrusion Detection

arXiv:2608.18155v1 Announce Type: cross Abstract: Quantum machine learning (QML) for network intrusion detection (NIDS) is routinely reported to reach near-perfect accuracy, yet the most rigorous stud

JSL-DC: A Word-Level Japanese Sign Language Dataset with Linguist-Derived Descriptions for Distinguishing Confusable Signs

arXiv:2608.18412v1 Announce Type: new Abstract: Effective sign language (SL) acquisition is crucial for deaf children, yet 95% are born to hearing parents who often lack proficiency in SL. SL recognit

Ling-3.0 released all 6 base checkpoints: 2 sizes × 3 stages

AntLing has released the full six-checkpoint matrix for the Ling-3.0 base model. tiny: pretrained, mid-trained, WSM-merged flash: pretrained, mid-trained, WSM-merged The concrete artifact is six separ

NanoSleep: A Parameter-Efficient Hybrid Temporal Convolutional Network for Single-Channel Sleep Stage Classification

model-releasesarxiv-cs-lg

arXiv:2608.18571v1 Announce Type: new Abstract: Sleep stage classification from single-channel electroencephalography (EEG) is essential for wearable and home-based sleep monitoring. However, many dee

Need help choosing the right AI model/tool for a complete web app workflow

I currently have these models available through Ollama/cloud: And I’m using Claude, Codex, OpenCode, and Ollama as my coding/agent tools. I want to learn professional vibecoding — not just asking AI t

model-releasesr-ollama

Nine Emotion Centroids: A Label-Free Valence Axis That Transfers Across Four Modalities

arXiv:2608.18090v1 Announce Type: cross Abstract: Inside a modern language model sits a single internal direction that tracks how positive or negative a sentence feels. We show how to find this valenc

Pedagogical AI in Mental Health: A Tri-Stream Fine-Tuned LLM Framework for Automated Clinical Supervision and Risk Triage

arXiv:2608.18438v1 Announce Type: cross Abstract: Modern mental healthcare faces a critical shortage of senior supervisory oversight, leading to a 'supervision gap' where novice therapists manage high

Qwen3.8-27B scored 29/30 on AIME 2026 with FP8 + xhigh reasoning — BF16 vs FP8 results

I benchmarked Qwen3.8-27B on MathArena/aime_2026 dataset, comparing BF16 and FP8 weights at medium and xhigh reasoning effort. Interesting findings are: quantized FP8 xhigh is better than BF 16 medium

Rethinking Privileged Information in On-Policy Self-Distillation

arXiv:2608.18271v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) trains a student on its own responses using token-level supervision from the same model conditioned on privileged ref

safetyarxiv-cs-lg

Safe Domain Adaptation for Physics: Overcoming Nuisances, Label Shifts, and Simulation Priors

model-releasesarxiv-cs-lg

arXiv:2608.18190v1 Announce Type: new Abstract: Domain adaptation is widely used to make neural networks trained on simulations applicable to experimental data. Its premise is that the two domains dif

Selection, Recombination, or a Fresh Solve? A Candidate-Free Control for Single-Pass Test-Time Aggregation

arXiv:2608.18379v1 Announce Type: cross Abstract: When every candidate is wrong, correct-candidate selection is unavailable, yet the aggregation call can still solve the problem afresh. A correct aggr

Stability-Aware Feature Design for Robust Watermark Detection in Machine-Generated Text

arXiv:2608.18102v1 Announce Type: new Abstract: The widespread adoption of large language models (LLMs) has intensified the demand for principled methods to distinguish human from machine-generated te

Web agent economics are set by inference volume and each step is one inference call. A simple task (extract a field, fill a form, navigate a…

model-releasestogether-ai--x

Web agent economics are set by inference volume and each step is one inference call. A simple task (extract a field, fill a form, navigate a site) is 10 to 20 calls. A multi-site workflow runs into th

Aloha! 🌺Introducing Ornith-1.5, a family of open-source LLMs spanning 9B Dense, 35B MoE, and 397B MoE, trained with self-improving strategi…

model-releasesclem-delangue--x

Aloha! 🌺Introducing Ornith-1.5, a family of open-source LLMs spanning 9B Dense, 35B MoE, and 397B MoE, trained with self-improving strategies. It achieves state-of-the-art performance among open-sourc

Am I doing something wrong? Qwen 3.8 27B seems useless for agentic coding

I have been using local models on/off for like 2 years or so but never really used them extensively because the closed ones were always much better. Once Qwen 3.8 27B was released I decided to give it

Beyond the Trace: Coupling an Interpretable Reasoning-State Readout to Native MoE Routing

arXiv:2608.17638v1 Announce Type: new Abstract: What a reasoning model writes is only a partial record of the process that produces it. We introduce a two-level internal readout for mixture-of-experts

I am so tired of the PR.

model-releasesgary-marcus--x

I am so tired of the PR. How Anthropic's new results post would read without the PR: Claude orchestrated open-source protein design models, PXDesign, RFdiffusion, Genie, BoltzGen, from a 30k-token exp

I pushed Qwen3.8-27B limits again... Dflash2 - 134 tps on a RTX 3090

Edit: Title says 134 tps, it's actually 138 -- keep in mind my 3090 is power limited to 250w. Three days ago I released a hyper-optimized Qwen3.8-27B inference engine for an RTX 3090 (82 tps single re

Improving Complex Moire Removal with Generative Supervision

arXiv:2608.17883v1 Announce Type: new Abstract: The availability of high-quality paired data is essential for training learning-based image demoireing models. However, it remains challenging for exist

Key-Frame Reasoning with SAM3: Third Place Solution for the MeViS-Text Track of the 8th LSVOS Challenge

arXiv:2608.17279v1 Announce Type: new Abstract: This report presents a two-stage, training-free solution for the MeViS-Text track of the 8th LSVOS Challenge. The task requires a model to localize and

Leveraging existing sparse point annotations for benthic imagery dense segmentation

arXiv:2608.17561v1 Announce Type: new Abstract: The health of marine ecosystems is a critical indicator of global environmental change, yet the physical constraints of underwater observation and the i

Likelihood Hacking in Probabilistic Program Synthesis

arXiv:2603.24126v2 Announce Type: replace Abstract: When language models are trained by reinforcement learning (RL) to write probabilistic programs, they can artificially inflate their marginal-likeli

safetyarxiv-cs-lg

MANIGUARD: A Benchmark and Data Suite for Specification-Grounded Safety Evaluation and Improvement of Robotic Manipulation

model-releasesarxiv-cs-ro

arXiv:2608.17386v1 Announce Type: new Abstract: Foundation-model policies for robotic manipulation are advancing rapidly on task success, but rigorous evaluation of whether they succeed safely is stil

Local Ai

Mixture-of-Expert Blocks Contain Strong Hallucination Detection Signals

arXiv:2608.17687v1 Announce Type: new Abstract: Despite their widespread use, Large Language Models (LLMs) remain limited by a fundamental problem: the generation of plausible but false content, known

local-aiarxiv-cs-ai

Applications

Physics-Informed and Hybrid Machine Learning in Additive Manufacturing: Application to Fused Filament Fabrication

arXiv:2608.17246v1 Announce Type: new Abstract: This article investigates several physics-informed and hybrid machine learning strategies that incorporate physics knowledge in experimental data-driven

applicationsarxiv-cs-lg

Policy-Invariant Reward Shaping from LLM Feedback: A Framework for Hybrid RL Agents

arXiv:2608.18008v1 Announce Type: cross Abstract: Combining large language models with reinforcement learning is increasingly explored, yet the theoretical status of LLM-derived reward signals is ofte

Probing the Prefill: Detecting Code Vulnerabilities via Latent Activations

arXiv:2608.16970v1 Announce Type: cross Abstract: LLM-based code generation is now embedded in mission-critical pipelines, but defenses against vulnerable output remain post-hoc -- static analyzers, f

PTXBench: Benchmark and Adapt LLMs for GPU Kernel Optimization with Architecture-specific PTX

arXiv:2608.17379v1 Announce Type: cross Abstract: We introduce PTXBench, a benchmark for evaluating and adapting large language models (LLMs) to use architecture-specific PTX for GPU kernel optimizati

Q-Interference: Memory-Efficient Phase-Aware Quantum-Inspired Attention

arXiv:2608.17288v1 Announce Type: new Abstract: GPT attention measures token compatibility through dot-product similarity. This mechanism is simple, effective, and memory-efficient. But it does not ex

S^3AM: A Single-Stream SAM with Reliability-Calibrated Frequency Adapter for Multi-modal Salient Object Detection

arXiv:2608.17475v1 Announce Type: new Abstract: Vision foundation models have recently advanced multi-modal salient object detection (MSOD) through parameter-efficient tuning and prompt learning. Howe

SCENARIODIFF: A Scenario-level Guidance Framework for Multimodal Time Series Forecasting--Extended Version

model-releasesarxiv-cs-lg

arXiv:2608.17164v1 Announce Type: new Abstract: Textual context such as news, reports, and logs can provide valuable signals for time series forecasting, especially when future dynamics are driven by

Teach and Grow: An Agent-Centered Architecture for General Robot Learning

arXiv:2608.17209v1 Announce Type: cross Abstract: End-to-end vision-language-action (VLA) and world-action models offer an elegant route to general-purpose robotics, but their reliability is bounded b

Research

Towards Safer RAG: Only Agents Capable of System 2 Thinking may Access Untrusted Documents

arXiv:2608.17153v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has significantly enhanced the performance of large language models (LLMs), yet these systems remain vulnerable to

researcharxiv-cs-cl

A Large-Scale Chinese Knowledge Graph-Text Alignment Dataset for Benchmarking Knowledge-Grounded LLMs

arXiv:2510.06039v2 Announce Type: replace-cross Abstract: Reliable evaluation of knowledge-grounded Large Language Models (LLMs) in Chinese requires resources that explicitly align Chinese-language te

A Unified DINOv2-Based Framework for LVEF Estimation, GLS Dysfunction Classification, and Early Cardiotoxicity Prediction

arXiv:2608.14750v1 Announce Type: cross Abstract: Left ventricular ejection fraction (LVEF) estimation (Task 1), global longitu-dinal strain (GLS)-based dysfunction classification (Task 2), and early

Aborted but Not Forgotten: KV-Cache Retention Breaks Rollback Consistency in Language Agents

arXiv:2608.15939v1 Announce Type: new Abstract: Stateful language agents assume a rejected branch can be taken back by clearing it from the application transcript. We show this breaks when the serving

Benchmarking Identity-Sensitive LLM Outputs for Surveillance and Security Robots

model-releasesarxiv-cs-ro

arXiv:2608.16030v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to generate textual robot design specifications, interaction policies, and risk assessments during ea

Beyond Asking: A Pipeline for Personalized Game Generation that Reads Players from Behavior

arXiv:2608.16196v1 Announce Type: new Abstract: Personalized game generation requires inferring a player's abilities and behavioral style from how they play. Large language models have made this infer