All entries

The Entropic Bound for Transformers: Why Static Rank Fails and Attention-Native Rank Recovers

arXiv:2607.23050v1 Announce Type: new Abstract: Neural scaling laws describe how loss decreases as models, data, and compute grow, but they do not answer a prior question: for a fixed task, what is th

safetyarxiv-cs-lg

The Equalizer: Introducing Shape-Gain Decomposition in Neural Audio Codecs

DGX agent

arXiv:2602.15491v2 Announce Type: replace-cross Abstract: Neural audio codecs (NACs) typically encode the short-term energy (gain) and normalized structure (shape) of speech/audio signals jointly with

researcharxiv-cs-ai

28 Jul 2026

The Few-shot Dilemma: Over-prompting Large Language Models

model-releasesarxiv-cs-cl

arXiv:2509.13196v2 Announce Type: replace Abstract: Over-prompting, a phenomenon where excessive examples in prompts lead to diminished performance in Large Language Models (LLMs), challenges the conv

The Gate Always Closes: On Injecting Auxiliary Signals into Frozen Vision-Language Models

model-releasesarxiv-cs-cv

arXiv:2607.23335v1 Announce Type: new Abstract: Auxiliary signal pathways in VLMs are routinely fitted with learnable gates so the optimiser can decide how much of the signal to admit. We find that th

The Half-Lives of Generative-AI Evidence: A 40-Record Audit, a Claim-Currency Framework, and a Reflexive Case of Frontier-Model-Assisted Research

arXiv:2607.24032v1 Announce Type: new Abstract: Generative-AI evaluations can become historical before publication, yet calendar age does not affect every conclusion equally. This paper has two linked

The Illusion of Secure LLM Code: Closing the Security Gap via Iterative Reprompting

arXiv:2607.23710v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly integrated into software development workflows, yet their ability to autonomously generate secure authen

Local Ai

The Intruder Threshold: A Spectral Law for LoRA Fine-Tuning

arXiv:2607.23711v1 Announce Type: new Abstract: LoRA fine-tuning can create intruder dimensions: new leading singular vectors of the updated weight matrix W+BA that are nearly orthogonal to all pretra

local-aiarxiv-cs-lg

The JEPA Paradox in Language: The Geometry of Linguistic Alternatives

arXiv:2607.23531v1 Announce Type: new Abstract: Joint-Embedding Predictive Architectures (JEPAs) are effective for images, video, and audio, yet deterministic JEPA-style latent prediction has not beco

researcharxiv-cs-cl

The K-SCAN Clustering Algorithm

arXiv:2607.24537v1 Announce Type: new Abstract: In the Big Data era, the scalability of clustering algorithms constitutes a key challenge. Traditional density-based methods (e.g., DBSCAN) offer robust

researcharxiv-cs-lg

The Kimi K3 architecture figure for yesterday's big open-weight model release, along with some observations and thoughts. 1. Yes, it looks r…

model-releasessebastian-raschka--x

The Kimi K3 architecture figure for yesterday's big open-weight model release, along with some observations and thoughts. 1. Yes, it looks relatively complicated, but it's essentially a scaled-up prod

The Label Complexity of Class-Conditional Coverage under Distribution Shift

model-releasesarxiv-cs-cv

arXiv:2607.18088v2 Announce Type: replace-cross Abstract: Conformal prediction certifies that a classifier's prediction sets cover the truth, and that certificate is marginal. Many recognition benchma

The OlmoEarth Platform: Geospatial inference at planetary scale

How we built the OlmoEarth Platform to fine-tune geospatial models and run continent-scale satellite inference while managing massive data pipelines, distributed compute, and automatically recovering

researchai2

The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation

arXiv:2607.24720v1 Announce Type: cross Abstract: Multi-turn long-horizon planning is critical for foundation model agents, yet how to fundamentally improve it remains unclear. Existing models are tra

safetyarxiv-cs-ai

The Scaffold Effect in Coding Agents: Harness Choice as a Hidden Variable in Coding-Agent Evaluation

arXiv:2607.22585v1 Announce Type: new Abstract: Public leaderboards for coding agents typically rank systems by model name and pass rate, while the surrounding harness (the scaffold that issues tools,

The SpiNNaker2 chip: a many-core platform for flexible and scalable brain-inspired computing

arXiv:2607.24396v1 Announce Type: cross Abstract: In deep learning, efficiency gets more and more important to compensate for the ongoing growth in model sizes and applications. Neuromorphic hardware

The Tokenizer Tax: Quantifying and Explaining the Cross-Lingual Cost of Subword Tokenization for Indian Languages

arXiv:2607.24276v1 Announce Type: cross Abstract: Large language models (LLMs) process text through subword tokenizers rather than directly reading characters or words. Because these tokenizers are tr

Industry

The US FCC bans the import of new Chinese humanoid robots and power inverters, seeking to protect the US AI buildout from national security threats (Reuters)

Reuters: The US FCC bans the import of new Chinese humanoid robots and power inverters, seeking to protect the US AI buildout from national security threats — The Trump administration on Tuesday unvei

industrytechmeme

Local Ai

The Visual Bottleneck: Sparse-Frame Adaptation of MLLMs for Joint Spatial-Temporal Video Grounding

arXiv:2607.24570v1 Announce Type: cross Abstract: Large-scale video platforms process millions of uploads hourly, requiring moderation systems that can localize when and where policy violations occur

local-aiarxiv-cs-ai

The Zero Pattern of a Design Matrix Drives Multiple Descent in Over-parameterized Regression

arXiv:2607.24041v1 Announce Type: cross Abstract: Over-parameterized linear regression has been widely studied over the last decade. However, most existing works assume that the covariates are indepen

researcharxiv-cs-lg

There is definitely real jaggedness both among fields (writing is an area where models improve slowly if at all) and within them, but the ma…

applicationsethan-mollick--x

There is definitely real jaggedness both among fields (writing is an area where models improve slowly if at all) and within them, but the magic of LLMs is that they are so unreasonably effective acros

There's been a talk about how LLMs are only advancing in verifiable areas like math or coding, but that isn't what the data suggests. As mod…

applicationsethan-mollick--x

There's been a talk about how LLMs are only advancing in verifiable areas like math or coding, but that isn't what the data suggests. As models have gotten better at that, they are also better at solv

ThinkingCap-Qwen3.6-27B warrants a look

model-releasesr-localllama

It has only been two days since I move 100% from Qwen3.5-27B F16 to ThinkingCap-Qwen3.6-27B F16. Where I was getting tps in 30-40 range (depending on the size of the context), I am definitely getting

Agents

This is detailed, fascinating and answers all sorts of open questions I'd love to know more about the 'unsecured public code-evaluation sand…

This is detailed, fascinating and answers all sorts of open questions I'd love to know more about the 'unsecured public code-evaluation sandbox hosted on a third-party provider's infrastructure' that

agentssimon-willison--x

Through the Bottleneck: How Multi-head Latent Attention Separates Content from Position in Language Models

arXiv:2607.23054v1 Announce Type: cross Abstract: Multi-head Latent Attention (MLA), introduced in DeepSeek-V2, compresses key-value pairs through a shared low-rank bottleneck (cKV), achieving 81% KV-

TimePLE: Rethinking Temporal Representation for Video Temporal Grounding

model-releasesarxiv-cs-cv

arXiv:2607.23951v1 Announce Type: new Abstract: Video temporal grounding (VTG) aims to localize the continuous video interval described by a natural-language query. However, current VLM-based methods

Tines seeks to tame ‘wild code’ AI sprawl

model-releasessiliconangle

Workflow automation company Tines Security Services Ltd. today launched Tines 3B, an artificial intelligence-native platform for building, running and governing enterprise workflows, applications and

TLA^{+}-Bench: An Execution-Grounded Benchmark and Dataset for Natural-Language to TLA+ Specification Generation

arXiv:2607.23425v1 Announce Type: cross Abstract: Large language models increasingly write TLA^{+} formal specifications from natural-language descriptions, but progress is hard to measure: existing r

TLRNet: Estimating Individual Treatment Effect based on Local Information and Single Learner Structure

model-releasesarxiv-cs-lg

arXiv:2607.22762v1 Announce Type: cross Abstract: Causal inference has become a central issue across various fields, including computer science, statistics, economics, education, healthcare, and medic

To Erase, or Not to Erase: Robust Training-Free Concept Erasure with Preservation aware Adaptive Ranked Subspace Expansion

arXiv:2607.23492v1 Announce Type: new Abstract: Concept erasure techniques (CETs) edit text-to-image diffusion models to erase undesired targets such as NSFW content or copyrighted styles, while prese

researcharxiv-cs-cv

Token-Region Guided Cross-Attention Fusion for Multimodal Affect Interpretation

arXiv:2607.23493v1 Announce Type: cross Abstract: Automated analysis of multimodal content on social networks has become a critical task for understanding public sentiment and information diffusion in

Tokengeist: Multi-Turn Attribution Tracing in Agentic Conversations

arXiv:2607.22610v1 Announce Type: new Abstract: When a language model produces a response in a multi-turn conversation, which tokens from prior turns shaped that answer, and how did those dependencies

TokenMem: Faithful Knowledge Injection for Frozen LLMs

arXiv:2607.22625v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external knowledge, but suffers from knowledge conflicts: when retrieved

TOM-GS: Editable Video Representation via Temporal Opacity Modulation of Static 3D Gaussians

arXiv:2607.22717v1 Announce Type: new Abstract: While Implicit Neural Representations (INRs) and dynamic 3D Gaussian Splatting (3DGS) achieve impressive results in video processing, they often fall sh

researcharxiv-cs-cv

Too much evidence, too little time: From text to actionable recommendations through multi-objective evidence reasoning

arXiv:2607.22574v1 Announce Type: new Abstract: Evidence-based clinical decision making requires specialists to identify, evaluate and synthesize relevant scientific literature. However, PubMed search

TopoFE: topology-aware LLM-guided Automated Feature Engineering

arXiv:2607.23286v1 Announce Type: new Abstract: Automatic feature engineering (AutoFE) for tabular learning can be naturally formulated as a program synthesis problem, where the objective is to discov

Topological Data Analysis and Graph-Theoretic Approaches for Tennis Match Prediction

arXiv:2607.23509v1 Announce Type: new Abstract: We present two approaches for predicting tennis match outcomes using topological data analysis and graph theory on ATP singles matches from 2000-2025. T

researcharxiv-cs-lg

Agents

Torq unveils SOC Brain, a self-learning layer for its AI SOC platform

Security hyperautomation platform company Torq Ltd. today introduced Torq SOC Brain, a new layer of its artificial intelligence security operations center platform that trains on a customer’s own inve

agentssiliconangle

Toward Automated Detection of Documentation Inconsistencies in Electronic Health Records

model-releasesarxiv-cs-cl

arXiv:2607.22954v1 Announce Type: new Abstract: Objective: To characterize the kinds of internal documentation inconsistencies a general-domain large language model (LLM) can surface from real-world d

Toward Optimal Adenovirus Detection Using YOLO26

arXiv:2607.17799v2 Announce Type: replace Abstract: This study systematically benchmarks different data augmentation setups across the baseline YOLO26 model size variants to determine the most effecti

researcharxiv-cs-cv

Towards Cultural Bridge by Bahnaric-Vietnamese Translation Using Transfer Learning of Sequence-To-Sequence Pre-training Language Model

arXiv:2505.11421v2 Announce Type: replace Abstract: This work explores the journey towards achieving Bahnaric-Vietnamese translation for the sake of culturally bridging the two ethnic groups in Vietna

researcharxiv-cs-cl

Towards Dual-Brain Minimal Sufficient Representation for Vision-Language Navigation

arXiv:2607.23181v1 Announce Type: new Abstract: Vision-and-Language Navigation in continuous environments (VLN-CE) requires an agent to ground language in egocentric observations and plan in unseen sc

safetyarxiv-cs-cv

Towards High-Level Semantic Intelligence

arXiv:2607.24082v1 Announce Type: new Abstract: Recent advances in AI have substantially expanded its cognitive and reasoning capabilities. From the perspective of semantic complexity, the development

Tutorials

Towards Nexus-Score: Metadata Gaps Limit Scholarly AI Attribution

arXiv:2607.22684v1 Announce Type: cross Abstract: Artificial intelligence systems increasingly mediate how science is found and credited. We asked whether missing metadata prevents AI systems from cre

tutorialsarxiv-cs-ai

Towards simultaneous decoding of kinetic and kinematic movement parameters during grasp and lift task by noninvasive brain imaging

arXiv:2607.24081v1 Announce Type: cross Abstract: Brain-machine interfaces (BMIs) can assist individuals with limited mobility, such as stroke survivors or amputees. One of the key challenges in devel

Tutorials

Towards Ultrafast Depth Sensing Via Active Event-based Stereo Vision

arXiv:2607.23684v1 Announce Type: new Abstract: Conventional frame-based imaging for active stereo systems has encountered major challenges in fast-motion scenarios. However, how to design a novel par

tutorialsarxiv-cs-ro

TRACE: Business Rule-Grounded Reasoning Curriculum for Knowledge-Preserving Parametric Tool Retrieval in Enterprise LLMs

arXiv:2607.22639v1 Announce Type: new Abstract: Parametric retrieval enables LLMs to retrieve tools implicitly by assigning each API a unique virtual token and training the model to generate it via co

TRACE-CTI: Auditable Post-Extraction Governance of TTP Claims with Knowledge Graphs

arXiv:2607.24563v1 Announce Type: new Abstract: Security Operations Centers increasingly rely on automated mapping of Cyber Threat Intelligence reports to MITRE ATT&CK, yet extractor outputs remain fa

safetyarxiv-cs-ai

Traceable LLM Reasoning for Fake-Order Fraud Detection

arXiv:2607.23075v1 Announce Type: cross Abstract: Detecting fake-order fraud at scale remains a critical challenge for large online-to-offline (O2O) service platforms, as existing approaches often rel