Search: “models”

OpenCode + llama.cpp + unsloth/Qwen3.8-27B-GGUF:Q6_K_XL = only failure so far

Hi, I have been using opencode with openrouter for quite a while now. Having read the success stories of using Qwen3.8-27B, I thought of trying it too. But every attempt has been a failure for me so f

22 Aug 2026

Safety

A knowledge-guided agentic framework for mitigating patient-context ambiguity in health queries

DGX agent

arXiv:2608.19875v1 Announce Type: cross Abstract: Patients often submit short, underspecified queries to healthcare chatbots that lack the patient-specific information needed to determine an appropria

safetyarxiv-cs-ai

21 Aug 2026

A Layered Simplex Architecture for Large Alphabets

arXiv:2608.19908v1 Announce Type: cross Abstract: Probability estimation over large alphabets under log loss is a well-studied problem, with celebrated methods such as the Good-Turing estimator. We in

Active Inference as Context Acquisition for AI Agents

arXiv:2608.19202v1 Announce Type: new Abstract: Interactive AI agents must acquire the right context as efficiently as possible. When a user omits a constraint, preference, file, or task variable, an

An Inclusive and Lightweight Approach to Federated Continual Learning for Cultural Heritage

arXiv:2608.20038v1 Announce Type: cross Abstract: Artificial intelligence can support cultural heritage and digital humanities through large-scale retrieval and analysis of digitized collections. Howe

CarBench: A Comprehensive Benchmark for Neural Surrogates on High-Fidelity 3D Car Aerodynamics

arXiv:2512.07847v2 Announce Type: replace Abstract: Benchmarking has been the cornerstone of progress in computer vision, natural language processing, and the broader deep learning domain, driving alg

Causal Inference under Interference with Learned Exposure Mappings

arXiv:2608.19224v1 Announce Type: cross Abstract: Exposure mappings are often assumed to be known in causal spillover analyses. In environmental settings, however, they are typically induced by transp

local-aiarxiv-cs-ai

CharTool: Tool-Integrated Visual Reasoning for Chart Understanding

arXiv:2604.02794v2 Announce Type: replace Abstract: Charts are ubiquitous in scientific and financial literature for presenting structured data. However, chart reasoning remains challenging for multim

local-aiarxiv-cs-ai

Applications

CLaST: Context-aware Contrastive VAE for Probabilistic Time Series Forecasting

arXiv:2608.20025v1 Announce Type: new Abstract: Probabilistic forecasting models are widely used for time series forecasting in domains such as energy systems, finance, medicine, and transportation. I

applicationsarxiv-cs-lg

Applications

DecoVAE: a Lightweight Interpretable Trend-Seasonal VAE Framework for Efficient Probabilistic Time Series Forecasting

arXiv:2608.20052v1 Announce Type: new Abstract: Probabilistic time series forecasting remains challenging, largely because modeling distinct trend and seasonal dynamics requires specialized approaches

applicationsarxiv-cs-lg

Deep-MKV-TS: Path-Dependent McKean--Vlasov Control for Financial Time Series Generation

arXiv:2608.19394v1 Announce Type: cross Abstract: We introduce Deep-MKV-TS, a path-dependent McKean-Vlasov framework for financial scenario generation. The stochastic dynamics are chosen by matching s

researcharxiv-cs-lg

Discrete Diffusion Inference-Time Control with Nested Sequential Monte Carlo

arXiv:2608.20123v1 Announce Type: cross Abstract: We study inference-time control for text generation in discrete diffusion language models, where the goal is to steer sampling toward sequence-level r

researcharxiv-cs-lg

DraftFM: A FoundationModel for Day-Zero Drafting in Magic: The Gathering

arXiv:2608.19568v1 Announce Type: cross Abstract: Drafting a new Magic: The Gathering expansion begins before any pick from it has been observed: the complete card list is public, but the draft logs t

Tutorials

Exploiting Completeness Perception with Diffusion Transformer for Unified 3D MRI Synthesis

arXiv:2602.18400v3 Announce Type: replace-cross Abstract: Missing data problems, such as missing modalities in multi-modal brain MRI and missing slices in cardiac MRI, pose significant challenges in c

tutorialsarxiv-cs-cv

FAR-DPO: Feasibility-Aware and Robust Direct Preference Optimization for Cyclic Peptide Design

arXiv:2608.19808v1 Announce Type: new Abstract: Cyclic peptides are emerging as promising molecular scaffolds in drug discovery due to their high binding affinity and structural stability. However, ex

Fastest NVFP4 quant of Qwen3.8 27B out there

Here's a brand new Blackwell-native, prefill-optimized 4-bit quant that runs 50% faster on compatible hardware than a Q4 quant of the same memory footprint. And it runs 4-7% faster than other NVFP4 qu

From Atari to EVE Online: Building on 15 Years of AI Research in Games

model-releasesgoogle-deepmind

This paper traces the expansion of AI research in games over a 15‑year period, from early Atari benchmarks to contemporary MMORPGs such as EVE Online. It introduces SIMA 2, an agent designed to play,

From Noise to Signal: Improving Security Log Anomaly Detection Using LLMs with Endpoint-Specific Logs

arXiv:2608.19938v1 Announce Type: cross Abstract: Existing approaches to anomalous behaviour log detection, such as Wazuh rely primarily on predefined detection rules, while statistical anomaly detect

Gallileo-4D: Frozen Backbone Ensemble for Dynamic 4D Reconstruction

arXiv:2608.19743v1 Announce Type: new Abstract: We describe our entry to the PhysAI Dynamic 4D Reconstruction Challenge, which placed third of 27 teams at 0.58356 APD on the final leaderboard, without

I tried to do agenic coding with Qwen 3.8 27B 3bit quant on a macbook air m2 24gb. It took 63 hours, but amazingly, the flight simulator worked.

I used LM Studio Bionic with Qwen 3.8 27B Q3_K_S with 57k context. It took a staggering 63 hours to finish coding. After the first prompt 'Create a beautiful, relaxing flight simulator in a single HTM

In 1948, a 32-year-old at Bell Labs published a paper nobody fully understood. Engineers found it too mathematical. Mathematicians found it …

model-releaseselon-musk--x

In 1948, a 32-year-old at Bell Labs published a paper nobody fully understood. Engineers found it too mathematical. Mathematicians found it too engineering-focused. One prominent mathematician reviewe

Inter-X++: A Comprehensive Benchmark for Multimodal Human-Human Interaction Analysis

arXiv:2608.20312v1 Announce Type: new Abstract: The capability to perceive and synthesize human-human interactions is fundamental to developing intelligent digital human systems. However, existing dat

Kahler landscapes for complex neural network descents and guarantees including a search and destroy of the Calabi-Yau manifold

arXiv:2608.19584v1 Announce Type: new Abstract: We study landscapes for complex-parameterized networks. Our approach is motivated with an information-theoretic manifold perspective of the parameter an

Learning to Beat: Phenotype-Guided Latent Flow with Regional Motion Priors for Biventricular Motion Synthesis

arXiv:2608.19738v1 Announce Type: cross Abstract: Full-cycle biventricular geometry is essential for characterizing cardiac function. However, dense and temporally consistent 3D+t biventricular meshes

Llama.cpp DSpark PC Tree Fork (up to 3%-29.5% faster!)

Hello gang, I made an implementation of DSpark PC Tree (Parent conditioned drafting tree). This is an implementation of this research paper: https://arxiv.org/abs/2608.02123 Unaffiliated, just found i

MaliciousSkillBench: A Comprehensive Benchmark for Malicious Agent Skill Detection

arXiv:2608.19901v1 Announce Type: cross Abstract: Agent Skills extend LLM agents with reusable instruction packages that may also include scripts, resources, and service configuration. This creates a

Maximum Likelihood Reinforcement Learning

arXiv:2602.02710v2 Announce Type: replace Abstract: Reinforcement learning (RL) is the method of choice for training models in setups where the objective function can only be evaluated by sampling fro

researcharxiv-cs-lg

PEA-DPO: Perception-Enhanced Alignment Direct Preference Optimization for MLLMs Alignment

arXiv:2608.19598v1 Announce Type: cross Abstract: Direct Preference Optimization (DPO) has emerged as an effective approach for aligning large language models (LLMs) with human preferences. However, i

Planning-Oriented End-to-End Autonomous Driving: Architectures, Evaluation, and Emerging Paradigms

model-releasesarxiv-cs-ro

arXiv:2608.20111v1 Announce Type: new Abstract: End-to-end autonomous driving has evolved from camera-to-control regression toward planning-oriented systems that use structured representations, trajec

Quantum Gaussian processes for prediction of channel observations

arXiv:2608.19306v1 Announce Type: cross Abstract: Given a set of input states, we consider the task of predicting the expectation value of a Pauli observable at the output of an unknown quantum evolut

Qworld: Question-Specific Evaluation Criteria for LLMs

arXiv:2603.23522v2 Announce Type: replace-cross Abstract: Evaluating large language models (LLMs) on open-ended questions is difficult because response quality depends on the question's context. Binar

researcharxiv-cs-ai

Remember, Verify, or Ask? Cross-Family Evaluation of Memory Commitment in LLM Agents

model-releasesarxiv-cs-cl

arXiv:2608.19564v1 Announce Type: new Abstract: Persistent memory can personalize an LLM agent, but an incorrect durable update can silently distort future behavior. We study the memory-clarification

SafeBranch: Branch-Pair Safety Alignment for Embodied Agents

arXiv:2608.19729v1 Announce Type: new Abstract: Vision-language-model-based embodied agents can complete instructed tasks but often violate safety constraints in the process, a problem recently framed

SAPO: Single-Rollout Autoregressive Policy Optimization for Agentic Reinforcement Learning

arXiv:2608.19842v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) has become a critical stage in the post-training of large language models. Existing critic-free, group-relative meth

Spike-based Belief Propagation in Nonlinear Dynamical Systems

arXiv:2608.19907v1 Announce Type: new Abstract: This paper presents a Bayesian control framework that integrates spike-based dynamics with probabilistic inference for adaptive control. Bayesian infere

The Asymmetric Harms of LLM Compression

arXiv:2608.19670v1 Announce Type: new Abstract: Large language models (LLMs) compression reduces deployment costs, but standard aggregate metrics like perplexity and accuracy often mask underlying beh

safetyarxiv-cs-cl

Tutorials

The Thousand Brains Theory 2.0: An Extension for the Long-Range Connections of the Neocortical Heterarchy

arXiv:2507.05888v2 Announce Type: replace-cross Abstract: Vernon Mountcastle hypothesized that the basis for intelligence in mammals is the replication of a general computational unit, the cortical co

tutorialsarxiv-cs-ai

This week’s ChatGPT feature drop - Aug 21: Another Friday, another roundup of what we shipped this week: 1/ Recent photos: Long press on + m…

This week’s ChatGPT feature drop - Aug 21: Another Friday, another roundup of what we shipped this week: 1/ Recent photos: Long press on + menu to quickly attach recents on iOS - this is a fun, power

model-releasesopenai--x

Video Evidence to Reasoning Efficient Video Understanding via Explicit Evidence Grounding

arXiv:2601.07761v2 Announce Type: replace Abstract: Large Vision-Language Models (LVLMs) face a fundamental dilemma in video reasoning: they are caught between the prohibitive computational costs of v

safetyarxiv-cs-cv

XDen-1K: A Density Field Dataset of Real-World Objects

arXiv:2512.10668v2 Announce Type: replace Abstract: A deep understanding of the physical world is essential for robotic manipulation and physically realistic simulation. While current methods, includi

Automated Computational Energy Minimization of ML Algorithms using Constrained Bayesian Optimization

arXiv:2407.05788v2 Announce Type: replace-cross Abstract: Bayesian optimization (BO) is an efficient framework for optimization of black-box objectives when function evaluations are costly and gradien

researcharxiv-cs-ai

Autonomous Agricultural Tractor: Integrated Weed Detection and LiDAR Navigation for Precision Paddy Farming

arXiv:2608.19004v1 Announce Type: cross Abstract: Site-specific weed management in paddy farming offers substantial reductions in herbicide use over conventional broadcast spraying, but field deployme

Beyond Predictive Fairness: Quantifying Attribution Consistency Across Demographic Groups in Diabetic Retinopathy Screening

arXiv:2608.18759v1 Announce Type: cross Abstract: Fairness in medical imaging is commonly evaluated through subgroup performance metrics, yet it remains unclear whether models rely on consistent visua

Beyond receptive fields: sequence-pooled normalization can supply most of a sequence labeler's context

arXiv:2608.18576v1 Announce Type: new Abstract: A convolutional sequence labeler's receptive field is routinely treated as the extent of the model's usable context: it sets dilation schedules, bounds

local-aiarxiv-cs-lg

Beyond Teacher Likelihood: Group-Calibrated On-Policy Distillation for Long-Context Reasoning

arXiv:2608.19181v1 Announce Type: cross Abstract: On-policy distillation (OPD) trains a student on its own responses using dense token-level guidance from a stronger teacher. In long-context tasks, ho

Continual Reasoning Gym: Diagnosing and Harnessing Shared Reasoning in Continual RLVR

arXiv:2608.18574v2 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) commonly post-trains reasoning models on multiple tasks, while rerunning multitask RLVR (MTRL) as

safetyarxiv-cs-lg

Coupled-cluster molecular properties across the main group that extrapolate beyond training size

arXiv:2608.18346v1 Announce Type: cross Abstract: Coupled-cluster theory defines the accuracy standard for molecular electronic-structure properties but scales too steeply for routine application, whe

local-aiarxiv-cs-ai

Different Facets of Verbalised Overconfidence: an Interpretability Study

arXiv:2608.18106v1 Announce Type: cross Abstract: Large language models tend to overconfidence, giving assertive answers when the evidence suggests hedging or abstention. Using controlled reasoning sc

researcharxiv-cs-ai