Search: “model-releases”

Curriculum Matters: Data-Efficient Relational PFN Pretraining with Synthetic Data

arXiv:2607.29120v1 Announce Type: new Abstract: Relational Prior-Data Fitted Networks (PFNs) such as RDB-PFN approximate Bayesian inference over multi-table relational databases by pretraining on mill

Model Releases

DART: Dual-Axis Airborne Reachability-Gated Torque-Reaction for Off-Road Vehicle Jumps

DGX agent

arXiv:2607.29011v1 Announce Type: new Abstract: Traversing crests, ledges, and ditches at high speed often launches vehicles into the air, and a mishandled landing presents a substantial crash hazard.

model-releasesarxiv-cs-ro

3 Aug 2026

DASH-OPD: Discrepancy-Aware Switching with Hysteresis for On-Policy Distillation

arXiv:2607.29078v1 Announce Type: new Abstract: On-policy distillation (OPD) trains student models on their own rollouts to reduce exposure bias. However, in multi-turn agent scenarios, early student

'Data center in a Box (on Wheels)' 256Gb VRAM/512Gb RAM AI Server 6-8 Month Operational Review, Stability Write Up, Benchmarks

I've been out of these forums for awhile but I figured I would provide a formal update on how this has been going now that it has some operation time under its belt, just to put the information out th

Data Turnstile: A Scalable Open Framework for Function-Calling Data Generation

arXiv:2607.29250v1 Announce Type: new Abstract: Small language models (SLMs) are attractive for agentic deployment due to low latency, reduced cost, and on-device privacy, yet they struggle with tool-

DeepSeek V4 Flash 0731 - Happy Numbers (700pp/18tg) and Thoughts

Originally, I was only getting around 140pp/s and about 21tg/s, but the config with -b 8192 -ub 8192 --cpu-moe is vastly superior, let's say 700pp/s and 18tg/s in the most relevant range. Test System:

DeepSeek V4-Flash (284B MoE) at 33 tok/s single / 68 tok/s aggregate on 2× RTX 3090 + a used quad-Xeon DDR4 server — full config

Ran DeepSeek V4-Flash-0731 — the full official checkpoint, not a re-quant — on commodity used hardware. Sharing because I couldn't find anyone else publishing Ampere results for this engine. Why bothe

Detecting AI-Generated Videos with Spiking Neural Networks

arXiv:2605.05895v2 Announce Type: replace-cross Abstract: Modern AI-generated videos are photorealistic at the single-frame level, leaving inter-frame dynamics as the main remaining axis for detection

Detecting Experiential Intertextuality Across Migration Routes: Beyond Surface Similarity in French Narratives

arXiv:2607.29188v1 Announce Type: new Abstract: Migrants traversing geographically distinct routes such as the Trans-Saharan and Balkan corridors often recount strikingly parallel lived experiences: p

Devtools must be open source (exe.dev)

model-releasessimon-willison

My comment on Devtools must be open source (exe.dev) — Hacker News.One of the arguments for open source software for end-users has always been the freedom to examine and modify how that software works

DiffAttack: Evasion Attacks Against Face Recognition via Latent Diffusion Models

arXiv:2607.28936v1 Announce Type: cross Abstract: Facial biometric identification relies on the distinctiveness of user attributes within a high-dimensional embedding space. However, the decision boun

Differentially Private Nonparametric Modal Learning with Applications to Regression and Clustering

arXiv:2607.29675v1 Announce Type: cross Abstract: Density modes provide a localized and interpretable summary of multimodal distributions, but their estimation under rigorous differential privacy cons

Dimensionality reduction for homological stability and global structure preservation

arXiv:2503.03156v4 Announce Type: replace-cross Abstract: We propose DiRe, a force-directed dimensionality reduction framework designed to preserve global structure and homological features while rema

Distilling Knowledge from Large Language Models into Lightweight Reinforcement Learning Agents for Autonomous Cyber Operations

arXiv:2607.28826v1 Announce Type: new Abstract: Autonomous Cyber Operations (ACO) are increasingly important for defending enterprise networks as cyber threats continue to evolve in sophistication. AC

Döner Bench DeepSeek-V4-Flash IQ2_XS running on a single RTX 3090

https://preview.redd.it/3zcvpbds14hh1.png?width=1911&format=png&auto=webp&s=a79aafb71eeca97638da93d2591902631e897fd5 I tried a test similar to the recent model-quant comparisons, but this time I focus

DungeonBench: A Benchmark for Rules-Rich Tactical Reasoning in Dungeons & Dragons Combat

arXiv:2607.29577v1 Announce Type: new Abstract: Games and simulators make valuable benchmarks by turning decisions into measurable outcomes, but many current suites under-test rules-rich tactical reas

Dynamics-aware identification of governing equations from sparse and noisy data

arXiv:2607.29036v1 Announce Type: new Abstract: Sparse identification of nonlinear dynamics (SINDy) and PDE functional identification (PDE-FIND) recover parsimonious ordinary and partial differential

EarlyDx: An Admission-Anchored Benchmark for Open-Ended Generation of Evidence-Supported ED-Encounter Diagnoses

arXiv:2607.28788v1 Announce Type: new Abstract: Clinical diagnosis at hospital admission must be made rapidly from limited, incomplete evidence. Existing diagnosis-prediction benchmarks are poorly sui

EgoEverything: A Benchmark for Human Behavior Inspired Long Context Egocentric Video Understanding in AR Environment

arXiv:2604.08342v2 Announce Type: replace Abstract: Long context egocentric video understanding has recently attracted significant research attention, with augmented reality (AR) highlighted as one of

Evaluating Federated Pre-Training: On the Reliability of Downstream Fine-Tuning and Intrinsic Evaluation

arXiv:2607.28658v1 Announce Type: cross Abstract: Federated pre-training offers a way to train foundation models on private or distributed data without centralizing the underlying datasets. However, e

Evaluation-Verification Reward for Consistent Multi-Reference Image Editing

arXiv:2607.29025v1 Announce Type: new Abstract: While recent image editing models have made rapid progress, multi-reference editing remains challenging, particularly in maintaining visual consistency

even within math, frontier models are far from being general intelligences. and we still need people to assess which of their output are tru…

model-releasesgary-marcus--x

even within math, frontier models are far from being general intelligences. and we still need people to assess which of their output are trustworthy and which are not. All frontier AI models (includin

ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction

arXiv:2607.29677v1 Announce Type: new Abstract: Enterprise workflows increasingly rely on agents for schema-guided extraction: given a document and a user-defined schema, the agent faithfully follows

Extrapolating the emergence of Hamiltonian chaos with random-feature Hamiltonian neural networks

arXiv:2607.28977v1 Announce Type: cross Abstract: Machine learning of Hamiltonian dynamics has driven growing interest in Hamiltonian neural networks (HNNs), which encode Hamilton's equations of motio

FairFund-Bench: Evaluating Distributive Bias in LLM Resource Allocation

arXiv:2607.28934v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly involved in the distribution of scarce resources, raising concerns about biased allocations based on cha

Fast Rates for Swap-Agnostic Learning of Proper Losses

arXiv:2607.28856v1 Announce Type: new Abstract: Swap-agnostic learning strengthens classical agnostic learning by allowing the comparator to select a different hypothesis on each level set of the lear

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients

arXiv:2607.29071v1 Announce Type: cross Abstract: Federated learning of foundation models faces a fundamental resource-asymmetry challenge: the institutions holding the most valuable domain-specific d

FlexComposer: Unified Video Compositing from Images to Dynamic Footage with Flexible Trajectory Control

arXiv:2607.29627v1 Announce Type: new Abstract: Generative video compositing, which involves inserting external assets seamlessly into existing video sequences, is essential for content creation and v

FriendBench: Benchmarking Dyadic Familiarity Inference in Humans and Multimodal Large Language Models

arXiv:2607.29602v1 Announce Type: cross Abstract: Reading a social situation often depends on behavior, not words alone. We introduce FriendBench, a benchmark for inferring whether two people are alre

Frontier AI performance across the business disciplines: a case-grounded benchmark of knowledge work and analytical reasoning

arXiv:2607.16057v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are improving rapidly as reflected in benchmark scores, yet these AI benchmarks largely test capabilities such as

Frugal Bayesian Optimization: Scalable Surrogates for Data- and Resource-Limited Discovery

arXiv:2607.29225v1 Announce Type: new Abstract: Bayesian Optimization (BO) is widely adopted for data-efficient optimization in scientific and engineering applications, yet its computational cost is r

GEMSS: A Variational Method for Discovering Multiple Sparse Solutions in Classification and Regression Problems

arXiv:2602.08913v3 Announce Type: replace Abstract: In underdetermined regression and classification problems, multiple feature subsets often yield equivalent predictive performance. In applied settin

Geographically Weighted Surrogate Models for Rapid Small-Area Chronic Disease Estimation

arXiv:2607.28655v1 Announce Type: cross Abstract: Small-area estimation (SAE) enables researchers and policymakers to identify spatial disparities in health outcomes, but survey-based SAE products car

GO-PRE: Goal-Oriented Next-Best-View Selection via Predictive Rendering Entropy for Active 3D Reconstruction

arXiv:2607.29037v1 Announce Type: new Abstract: Active 3D reconstruction relies on active view selection to maximize reconstruction fidelity under limited capture budgets. However, most existing metho

Harnessing the Wisdom of LLM Crowds through Complementarity-Driven Iterative Collaboration

arXiv:2607.29087v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in enterprise settings, yet individual models remain bounded by model-specific capability limitat

How to run big models on old hardware 30B at 22 tok/s on 6GB GPU and 16GB RAM

I have been working on this tool for months and there are a lot of new functionalities and tests that are going to be released in the next few weeks! The goal of the tool is to allow community members

model-releasesr-ollama

Hy-MultiTurn: A Six-Dimensional Benchmark for Deep Multi-Turn Dialogue Understanding

arXiv:2607.29196v1 Announce Type: new Abstract: Long-running multi-turn interactions with chatbots and agents are now common, and a correct response often depends on remembering earlier details, track

I compared MinerU, Granite-Docling, and PaddleOCR-VL on 12 PDF-parsing capabilities using 6 document types

I tested them by sending the 6 documents, each meant to represent a different document type, through my own webapp and comparing every output against the source. All ran on the same L4 GPU. The docume

I gave five different local LLMs a town. They invented Facebook and a duck-based credit bureau. (MIT, self-hosted, you don't play it — you watch it)

Each villager in Pepperton is a different model — a mistral, a qwen3, a qwen2.5, a phi4-mini, a llama3.2 — because model families have genuinely different temperaments, and the friction between them i

model-releasesr-ollama

Identifying Informative Environments for Cognition Parameter Inference via Bayesian Experimental Design

arXiv:2607.28894v1 Announce Type: new Abstract: Computational cognitive modeling seeks to infer latent cognitive mechanisms underlying observed behavior. Bayesian inverse planning provides a principle

Inference-time Trajectory Optimization for Structure-Preserving Manga Image Editing

arXiv:2603.27790v2 Announce Type: replace Abstract: We present a lightweight, training-free trajectory correction method that adapts a pretrained image editing model to each input manga image using on

InferQ: A Database-Oriented Benchmark for Quantum Circuits Simulation

arXiv:2607.29134v1 Announce Type: cross Abstract: Recent work suggests that relational database management systems (RDBMSs) can execute quantum circuit simulation by compiling the simulation into SQL

Is It Time for the Renaissance of Salient Object Detection in the Era of MLLMs?

arXiv:2607.29222v1 Announce Type: new Abstract: The zero-shot capabilities of multimodal large language models (MLLMs) are pushing salient object detection (SOD) beyond task-specific supervision. To d

KAT Coder 2.5 dev: Do yourself a favor and try it!

It is so good! I don't know why there aren't more people talking about it. Fewer tokens, faster and more accurate than Qwen 3.6 35b a3b. On my setup it's nearly as good as 27b, but 5x faster. And it c

Language Models Agree With Each Other, Not With Readers

arXiv:2607.29274v1 Announce Type: cross Abstract: Claims that language models homogenise are usually measured against human judgements collected for the study, which makes the human side an artifact o

LARA: Lightweight Adapters in the Residual Stream for Composable Adaptation and Alignment

arXiv:2607.28669v1 Announce Type: new Abstract: We present LARA (Lightweight Additive Residual Adaptation), a method for efficient adaptation that operates in the residual stream of a frozen model rat

Latent Sculpting for Zero-Shot Generalization: A Manifold Learning Approach to Out-of-Distribution Anomaly Detection

arXiv:2512.22179v3 Announce Type: replace Abstract: Detecting previously unseen attacks remains a major challenge for machine learning-based intrusion detection systems. Deep models trained on network

LayoutBench: Performance Benchmarking of Cloud Storage Layouts for Multimedia Data

arXiv:2607.28880v1 Announce Type: cross Abstract: Modern multimedia machine learning workloads increasingly store large-scale datasets in cloud object storage services such as AWS S3. How these sample