All entries

SpatialQ: Understanding 3D Gaussian Splatting Scene Quality via Visual-based MLLM

model-releasesarxiv-cs-cv

arXiv:2607.26595v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has emerged as an effective representation for novel view synthesis and 3D scene reconstruction, creating an increasing dem

Agents

SpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from Scratch

DGX agent

arXiv:2607.27167v1 Announce Type: cross Abstract: LLM-based agents excel at software engineering tasks where an existing codebase provides context, but constructing a program from scratch remains fund

agentsarxiv-cs-cl

30 Jul 2026

Speech2Grasp: Data-Efficient Transfer of Text-Conditioned Grasp Detection to Speech in Humanoid Robots

arXiv:2607.26567v1 Announce Type: cross Abstract: Humanoid robots increasingly require multi-modal understanding for natural interaction with humans. Despite the prominence of vision-language models,

applicationsarxiv-cs-cv

Spline-Based Boundary Representations for Sparse View Reconstruction and Simulation Using Isogeometric Analysis

arXiv:2607.26234v1 Announce Type: new Abstract: Image-based reconstruction aims to recover three-dimensional geometry from images. Recent advances have enabled the recovery of visually detailed models

SPROUT: A Scalable Diffusion Foundation Model for Agricultural Vision

arXiv:2603.27519v2 Announce Type: replace Abstract: Image-based plant phenotyping depends on dense structural understanding of crops, yet pixel-level annotation remains expensive across species, organ

Stable and Budget-Feasible Coalition Formation for Clustered Federated Learning: A Hedonic Potential-Game Approach

arXiv:2607.26788v1 Announce Type: cross Abstract: Clustered federated learning benefits from organizing heterogeneous participants into coalitions that train coalition-specific models, but such cluste

Tutorials

Stacked sessions and pull requests in the GitHub Copilot app

Learn how I modernized an old codebase of mine using stacked sessions and pull requests in the GitHub Copilot app. The post Stacked sessions and pull requests in the GitHub Copilot app appeared first

tutorialsgithub-ai-blog

Starting in 15 minutes

applicationstogether-ai--x

Starting in 15 minutes Kimi K3 has everyone’s attention. On July 30, hear @Kimi_Moonshot's Feihu Tang explain the architecture and decisions behind it. He joins Jue Wang and Zain Hasan from Together A

Tutorials

StatePlay: State-Aware Game World Models for Mechanics-Consistent Generation

arXiv:2607.26754v1 Announce Type: new Abstract: Recent game world models can generate visually realistic and interactive environments conditioned on player actions. However, games are not defined by p

tutorialsarxiv-cs-cv

Statistical laws and linguistics differ in naturalistic video and fictional conversations

arXiv:2512.18072v3 Announce Type: replace Abstract: Conversation is a cornerstone of social connection and is linked to well-being outcomes. Conversations vary widely in type with some portion generat

researcharxiv-cs-cl

Steering Instruction Hierarchies at Inference Time

arXiv:2607.26228v1 Announce Type: new Abstract: Instruction hierarchies are a core safety assumption of language model deployment: higher priority inputs, such as system prompts, should override confl

safetyarxiv-cs-cl

Step-Attention Refinement of DINOv3 Features for Efficient Anterior Eye Segmentation

arXiv:2607.27087v1 Announce Type: new Abstract: Anterior eye segment (AES) segmentation is a key component of both ocular biometrics and emerging clinical image analysis applications. However, heterog

Structurally Separated Uncertainty in Supervised Latent Variable Models

arXiv:2602.11219v2 Announce Type: replace Abstract: Predictive uncertainty is commonly decomposed into epistemic and aleatoric components, but standard decompositions often produce strongly correlated

StructureGS: Structure-aware Gaussian Splatting for Articulated Object Reconstruction

arXiv:2607.26889v1 Announce Type: cross Abstract: Reconstructing articulated objects with multiple movable parts is essential for understanding object structure and enabling physical interaction. Howe

sure we lose money on every inference but we make it up in volume

model-releasesgary-marcus--x

sure we lose money on every inference but we make it up in volume We are committed to pushing the model frontier across cost efficiency, capability, and speed. Starting today, we are reducing prices f

Tutorials

Surrogate assisted diversity estimation in neural ensemble search

arXiv:2607.26940v1 Announce Type: new Abstract: Ensembles are a standard way to improve the performance and robustness of deep neural networks, but their effectiveness crucially depends on both the qu

tutorialsarxiv-cs-lg

SymmGrid: Super-Scaling On-Robot Learning with Parallelized Symmetries and Egocentric-Exocentric Visual Perception

arXiv:2607.26985v1 Announce Type: cross Abstract: Deep reinforcement policy learning directly in physical robots (on-robot learning) remains bottlenecked by slow wall-clock training times. We present

Symphony of Bias: Exploring Gender Associations with Musical Instruments in Multimodal LLMs

model-releasesarxiv-cs-cl

arXiv:2607.26355v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly embedded in everyday life and widely used for information seeking, raising concerns about their potential

Task and Skill Planning: Hierarchical Robot Planning with Black-Box Skills

arXiv:2504.17901v3 Announce Type: replace Abstract: Task and motion planning (TAMP) is a well-established approach for solving long-horizon robot planning problems. Although TAMP methods have historic

applicationsarxiv-cs-ro

Temporally Centered SIGReg Improves Multi-Task LeWorldModel Learning: From Analysis to Method

arXiv:2607.26924v1 Announce Type: new Abstract: Recent work on LeWorldModel (LeWM) has shown that the Sketched Isotropic Gaussian Regularizer (SIGReg) enables stable end-to-end world-model learning fr

The Advantage of Fine-Grained Training

arXiv:2509.05130v2 Announce Type: replace Abstract: In classification problems, models are trained to predict a class label based on the input data features. However, class labels are organized hierar

// The agent is its own best speculator // Agents spend a large share of wall-clock time waiting on tool results. Speculation hides that lat…

// The agent is its own best speculator // Agents spend a large share of wall-clock time waiting on tool results. Speculation hides that latency by predicting and pre-executing the next call, but exte

safetydair-ai--x

The Art of Not Forgetting A Local Learning Architecture for Continual Learning

arXiv:2607.26523v1 Announce Type: new Abstract: We introduce CMP (Cognitive Memory Primitive), a continual-learning architecture that repre?sents inputs as sparse relational codes, stores them in a tw

The Confounder Trap: Treatment-Encoding Representations in Causal Inference with Text

arXiv:2607.26309v1 Announce Type: cross Abstract: Estimating causal effects of linguistic properties from observational text is difficult because the same document can contain both the treatment of in

safetyarxiv-cs-cl

The Download: tricking LLMs, and reviving geothermal plants

This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. A fundamental flaw leaves LLMs strikingly vulnerable to attack

researchmit-tech-review

The narrative: Blame the Agent, instead of the Agency that told him to “apply all your powers and told to achieve this win.” Ironically, man…

The narrative: Blame the Agent, instead of the Agency that told him to “apply all your powers and told to achieve this win.” Ironically, many forefront members of the AI-Safety community, in their fer

safetyyann-lecun--x

The Reliability of LLMs for Medical Diagnosis: An Examination of Consistency, Manipulation, and Contextual Awareness

model-releasesarxiv-cs-cl

arXiv:2503.10647v2 Announce Type: replace Abstract: This study evaluated the diagnostic reliability of two Large Language Models (LLMs), Google Gemini 2.0 Flash and OpenAI ChatGPT-4o, across three dim

The Rise of AI in Weather and Climate Information and its Impact on Global Inequality

arXiv:2603.05710v2 Announce Type: replace-cross Abstract: AI development's current trajectory risks automating and amplifying the North-South divide in the global climate information system. Frontier

applicationsarxiv-cs-lg

The Sparsity Ceiling: Where Spiking Networks Can and Cannot Trade Activity for Energy

arXiv:2607.26648v1 Announce Type: cross Abstract: Spiking neural networks (SNNs) are promoted as an energy-efficient substrate because sparse, event-driven activity replaces dense multiply-accumulates

researcharxiv-cs-lg

Local Ai

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents

arXiv:2607.26865v1 Announce Type: cross Abstract: LLM agents following the ReAct paradigm are promising enablers of complex multi-step tasks, including multi-hop question answering, code generation, a

local-aiarxiv-cs-lg

Thinking Machines just released Inkling-Small: 276B total, 12B active. A faster Inkling that matches or beats its 975B big brother in many b…

model-releasessoumith-chintala--x

Thinking Machines just released Inkling-Small: 276B total, 12B active. A faster Inkling that matches or beats its 975B big brother in many benchmarks. To test its speed, we plugged it into HF's speech

Thinking Under Uncertainty: Evidence Use and Information-Seeking in Language Models

arXiv:2607.26845v1 Announce Type: new Abstract: Inference-time thinking improves the performance of large language models, but aggregate outcomes do not reveal whether models use available evidence mo

This is absolutely wild... Anthropic reviewed their logs and found out that their own supposedly-sandboxed cyber evals had hacked three sepa…

model-releasessimon-willison--x

This is absolutely wild... Anthropic reviewed their logs and found out that their own supposedly-sandboxed cyber evals had hacked three separate companies back in April without them noticing! In a rev

Tight Generalization Bound for AdaBoost

arXiv:2607.26838v1 Announce Type: new Abstract: In this paper we show that the generalization error of AdaBoost is Thetaig(frac{dln(ngamma^{2}/d)}{ngamma^2}+frac{ln(1/elta)}{n}ig), where gamma is the

Time-delay Control Using a New Nonlinear Adaptive Law for Cable-Driven Robots

arXiv:2607.26383v1 Announce Type: cross Abstract: Cable-driven manipulators exhibit strong nonlinearities and low structural stiffness, which make precise control challenging under time-varying uncert

researcharxiv-cs-ro

TiPToP: A Modular Open-Vocabulary Robot Manipulation System That Plans

model-releasesarxiv-cs-ro

arXiv:2603.09971v2 Announce Type: replace Abstract: We present TiPToP, a modular manipulation system that integrates pretrained foundation models with a GPU-accelerated Task and Motion Planner to solv

Agents

Top-k Pareto Bandits: Hypervolume Regret for Multi-Objective Slate Selection

arXiv:2607.26273v1 Announce Type: new Abstract: We consider a stochastic multi-objective bandit problem where, at each round, the agent selects a slate of k arms and observes their d-dimensional rewar

agentsarxiv-cs-lg

Towards Grounded GI Endoscopy VQA via Multi-Task Learning on Small VLMs

arXiv:2607.27122v1 Announce Type: new Abstract: Gastrointestinal (GI) endoscopic image analysis has shifted from single-label classification toward visual question answering (VQA), where a model must

safetyarxiv-cs-cv

Towards Trustworthy Embodied Intelligence: A Systems Framework and Graded Trustworthiness Levels

model-releasesarxiv-cs-ro

arXiv:2607.26121v1 Announce Type: new Abstract: Embodied intelligence integrates learned perception and decision making with real-time computation, control, and physical interaction. Because failures

ToxScreen: Detecting Whether an LLM Has Been Poisoned

arXiv:2607.26849v1 Announce Type: cross Abstract: As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that c

TPCD: Tone-Pressure Contrastive Decoding and the Label-Free Gating Bottleneck in Vision-Language Models

model-releasesarxiv-cs-cv

arXiv:2607.26536v1 Announce Type: new Abstract: High-pressure prompts can push vision-language models (VLMs) into unsupported commitments, such as reading illegible text, reporting indeterminate times

TPD: Temporal Prior Decoupling for Text-to-Video Diffusion Models

arXiv:2607.26706v1 Announce Type: new Abstract: Text-to-video diffusion models generate temporally coherent content from natural language, yet when a prompt describes an early scene that persists whil

TraceCLIP: Recovering Local Semantics from Patch-to-CLS Contributions

arXiv:2607.26107v1 Announce Type: new Abstract: Dense vision-language understanding, including object localization, region recognition, and open-vocabulary semantic segmentation, requires associating

safetyarxiv-cs-cv

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation

arXiv:2510.00192v3 Announce Type: replace Abstract: Low-rank adaptation (LoRA) has become a widely used paradigm for parameter-efficient fine-tuning of large language models, yet its representational

Transformers Can Learn Rules They've Never Seen: Proof of Computation Beyond Interpolation

arXiv:2603.17019v2 Announce Type: replace Abstract: A central question in the debate over large language models is whether transformers can learn rules they have never seen, or whether they can only i

Local Ai

TREA-Net: A Transferable Residual Epidemiological Adaptation Network for Dengue Incidence Forecasting

arXiv:2607.26854v1 Announce Type: new Abstract: Accurate multi-week dengue forecasting supports timely vector-control interventions, outbreak preparedness, and healthcare resource allocation. However,

local-aiarxiv-cs-lg

TreeCCA: Canonical Correlation Analysis via Gradient-Boosted Trees

arXiv:2607.27027v1 Announce Type: new Abstract: Gradient-boosted trees dominate tabular machine learning, yet canonical correlation analysis has always relied on linear or neural encoders. We propose

TREK: A Travel Reasoning and Evaluation Kit for LLM Agents in Complex Trip Planning

model-releasesarxiv-cs-cl

arXiv:2607.26977v1 Announce Type: new Abstract: Travel planning is a demanding stress test for tool-using LLM agents: a usable itinerary is a single artifact that must be right along many axes at once