All entries

Hybrid TF--IDF Logistic Regression and MLP Neural Baseline for Indonesian Three-Class Sentiment Analysis on Social Media Text

arXiv:2605.07793v1 Announce Type: new Abstract: This paper presents a compact three-class sentiment analysis study for Indonesian social media text. The task is formulated with positive, negative, and

applicationsarxiv-cs-cl

Tutorials

HYPER: A Foundation Model for Inductive Link Prediction with Knowledge Hypergraphs

DGX agent

arXiv:2506.12362v3 Announce Type: replace-cross Abstract: Inductive link prediction with knowledge hypergraphs is the task of predicting missing hyperedges involving completely novel entities (i.e., n

tutorialsarxiv-cs-ai

11 May 2026

HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents

arXiv:2605.07177v1 Announce Type: cross Abstract: Existing multimodal search agents process target entities sequentially, issuing one tool call per entity and accumulating redundant interaction rounds

Tools

I believe the kids call this '@thinkymachines just brutally framemogged gdm and oai'. basically everyone's definition of 'realtime' just got…

I believe the kids call this '@thinkymachines just brutally framemogged gdm and oai'. basically everyone's definition of 'realtime' just got a massive frciking upgrade Media lowkey the funniest videos

toolsswyx--x

I built http://whichhumanoid.ai, the world's first buyer's directory for humanoid robots. Tesla Optimus, Figure 02, 1X Neo, Unitree R1, AgiB…

applicationsyohei-nakajima--x

I built http://whichhumanoid.ai, the world's first buyer's directory for humanoid robots. Tesla Optimus, Figure 02, 1X Neo, Unitree R1, AgiBot, Apptronik Apollo. Every robot side-by-side. Compare any

I have a new job! Excited to announce that I will be working with Hugging Face to make local models work great in OpenClaw and other open ag…

I have a new job! Excited to announce that I will be working with Hugging Face to make local models work great in OpenClaw and other open agent harnesses! I will be building in public and documenting

agentsclem-delangue--x

I have one big problem with agentic engineering: I want agents to operate autonomously, but I also want granular, reversible control over ev…

I have one big problem with agentic engineering: I want agents to operate autonomously, but I also want granular, reversible control over every change they make. I could solve this by committing every

agentsjerry-liu--x

Local Ai

I made a fixed-camera timelapse showing 2,000 years of Los Angeles evolution — from empty Tongva homeland to modern megacity. The camera never moves. Neither do the mountains.

local-air-stablediffusion

This post describes a fixed-camera timelapse visualization created using AI (likely Stable Diffusion) that depicts Los Angeles's transformation over 2,000 years, starting from its original state as To

🤯 i need all of you to stop what you're doing and look at this @webassembly + transformers.js + @googlegemma powered robot, running complet…

model-releasesclem-delangue--x

🤯 i need all of you to stop what you're doing and look at this @webassembly + transformers.js + @googlegemma powered robot, running completely offline I think Reachy is the one who needs chess lessons

Tools

I recently joined @latentspacepod to talk about AI for physics. We dug into recent work on scattering amplitudes with GPT, and what it sugge…

I recently joined @latentspacepod to talk about AI for physics. We dug into recent work on scattering amplitudes with GPT, and what it suggests about how AI will accelerate theoretical discovery in a

toolsswyx--x

I will not confirm nor deny whether I love these Parallel Agents

I will not confirm nor deny whether I love these Parallel Agents Meet Replit Parallel Agents Build faster by running up to 10 agents in parallel Each agent gets its own copy of your app They work on t

agentsreplit--x

ICDAR 2026 Competition on Writer Identification and Pen Classification from Hand-Drawn Circles

arXiv:2605.07816v1 Announce Type: new Abstract: This paper presents CircleID, a large-scale ICDAR 2026 competition on writer identification and pen classification from scanned hand-drawn circles. The

researcharxiv-cs-cv

Identifiability Challenges in Sparse Linear Ordinary Differential Equations

arXiv:2506.09816v3 Announce Type: replace Abstract: Dynamical systems modeling is a core pillar of scientific inquiry across natural and life sciences. Increasingly, dynamical system models are learne

If you believe this nonsense, and a lot of people do, I beg you to read my newsletter called “Misplaced Panic Over AI progress” 🙏

If you believe this nonsense, and a lot of people do, I beg you to read my newsletter called “Misplaced Panic Over AI progress” 🙏 we are exactly 4.5 steps away from achieving AGI!! People are not read

safetygary-marcus--x

if you've ever wanted a cofounder that would manage all your agents for you... try http://cofounder.co by @intelligenceco

Cofounder.co is a platform by Intelligence Co that provides AI agent management, allowing users to delegate agent oversight and coordination to an automated system rather than managing multiple agents

agentsyohei-nakajima--x

Tutorials

I'm delighted that @coursera and @udemy have come together as one company to serve learners. Both Coursera and Udemy were founded with the b…

I'm delighted that @coursera and @udemy have come together as one company to serve learners. Both Coursera and Udemy were founded with the belief that access to high-quality education changes lives. O

tutorialsandrew-ng--x

i'm no scott wu, but dabbled in math competitions in middle school and took 1st in state once but then switched to dance in high school and …

i'm no scott wu, but dabbled in math competitions in middle school and took 1st in state once but then switched to dance in high school and ranked #1 nationally in japan w the team and then did neithe

agentsyohei-nakajima--x

I'm starting office hours for Claude Code's cloud environments. If you use any of our cloud related features on desktop/web/mobile, come tal…

I'm starting office hours for Claude Code's cloud environments. If you use any of our cloud related features on desktop/web/mobile, come talk to me! Bring feature requests, bug reports, or anything in

model-releasesthariq--x

Industry

Imaging tech startup eyeo raises €40M to try to show the world in a very different light

Netherlands- and Belgium-based imaging technology startup eyeo B.V. said today it has closed on a €40 million ($47.07 million) Series A round of funding in order to try to fulfill its mission to enhan

industrysiliconangle

ImplantMamba: Long-range Sequential Modeling Mamba For Dental Implant Position Prediction

arXiv:2605.07082v1 Announce Type: new Abstract: In the design of surgical guides for implant placement, determining the precise implant position is a critical step. However, the implant region itself

researcharxiv-cs-cv

Implementing advanced AI technologies in finance

applicationsmit-tech-review

In finance departments that have long been defined by precision and control, AI has arrived less as a neatly managed upgrade than as a quiet insurgency. Employees are already using it while leadership

Implicit Compression Regularization: Concise Reasoning via Internal Shorter Distributions in RL Post-Training

arXiv:2605.07316v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards improves LLM reasoning but often induces overthinking, where models generate unnecessarily long reasoning

safetyarxiv-cs-ai

Tutorials

Implicit Multi-Camera System Calibration Using Gaussian Processes

arXiv:2605.07491v1 Announce Type: new Abstract: This paper proposes a novel framework for implicit multi-camera system calibration utilizing Gaussian Process (GP) regression. Conventional explicit cal

tutorialsarxiv-cs-cv

Implicit Preference Alignment for Human Image Animation

arXiv:2605.07545v1 Announce Type: cross Abstract: Human image animation has witnessed significant advancements, yet generating high-fidelity hand motions remains a persistent challenge due to their hi

Import AI 456: RSI and economic growth; radical optionality for AI regulation; and a neural computer

This newsletter covers three main topics: the relationship between AI capabilities relative to human intelligence (RSI) and its potential economic impacts, regulatory approaches that emphasize flexibi

safetyimport-ai

Important Nature Neuroscience paper shows how humans differ from LLMs. Many people currently believe that humans are just next-word predicto…

Important Nature Neuroscience paper shows how humans differ from LLMs. Many people currently believe that humans are just next-word predictors, like LLMs. But this new paper by Zou, Poeppel and Ding s

safetygary-marcus--x

Improved Model-based Reinforcement Learning with Smooth Kernels

arXiv:2605.07218v1 Announce Type: new Abstract: For continuous state-action space scenarios, classical reinforcement learning (RL) theory predominantly focuses on low-rank Markov decision processes (M

In a two-week UK High Court trial, Shein accuses Temu of 'industrial scale' copyright infringement of its photos; Temu says Shein is suing to stifle competition (Sam Tobin/Reuters)

Sam Tobin / Reuters: In a two-week UK High Court trial, Shein accuses Temu of “industrial scale” copyright infringement of its photos; Temu says Shein is suing to stifle competition — Online fast-fash

applicationstechmeme

In-Context Credit Assignment via the Core

arXiv:2605.06920v1 Announce Type: cross Abstract: We propose incentive-aligned mechanisms for in-context credit assignment: the task of assigning credit for AI-generated content (e.g. code, news artic

🚨 In his testimony just now, at the Musk-OpenAI trial, Satya Nadella came off as shrewd, calm, and (mostly) honest, an impressive leader – …

🚨 In his testimony just now, at the Musk-OpenAI trial, Satya Nadella came off as shrewd, calm, and (mostly) honest, an impressive leader – but also selectively blind. How? He seemed unable to believe

safetygary-marcus--x

In modern ML accelerators, FLOPS have absolutely exploded. Often though, the bottleneck is not FLOPS but memory bandwidth. Similarly, model …

researchsoumith-chintala--x

In modern ML accelerators, FLOPS have absolutely exploded. Often though, the bottleneck is not FLOPS but memory bandwidth. Similarly, model intelligence has exploded, causing the bottleneck to be huma

Tutorials

Inductive Power Grid Cascading Failure Analysis with GRU-Gated Graph Attention

arXiv:2605.07010v1 Announce Type: new Abstract: Identifying vulnerable transmission lines in power grids before a cascading failure occurs is challenging: existing methods can learn inter-line failure

tutorialsarxiv-cs-lg

Inference of Qualitative Models from Steady-State Data via Weighted MaxSMT

arXiv:2605.07433v1 Announce Type: cross Abstract: Qualitative models provide crucial instruments for modelling complex biological systems. While advances in automated reasoning and symbolic encodings

Inference-Time Attribute Distribution Alignment for Unconditional Diffusion

arXiv:2605.07456v1 Announce Type: new Abstract: Inference-time controllable generation is essential for real-world applications of unconditional diffusion models. However, most existing techniques foc

safetyarxiv-cs-lg

Inference Time Causal Probing in LLMs

arXiv:2605.07631v1 Announce Type: new Abstract: Causal probing methods aim to test and control how internal representations influence the behavior of generative models. In causal probing, an intervent

InfoGeo: Information-Theoretic Object-Centric Learning for Cross-View Generalizable UAV Geo-Localization

arXiv:2605.07099v1 Announce Type: new Abstract: Cross-view geo-localization (CVGL) is fundamental for precise localization and navigation in GPS-denied environments, aiming to match ground or UAV imag

safetyarxiv-cs-cv

Information-theoretic Limits of Learning and Estimation

arXiv:2605.06710v1 Announce Type: cross Abstract: Information theory plays a central role in establishing fundamental limits on what any learning or estimation algorithm can -- and cannot -- achieve,

Innovation abounds in device charging

The changes may be less perceptible than in smartphones, tablets, or wearables, but chargers have also been quietly reinvented over the last decade. At one time a bulky mix of tangled cables and conne

researchmit-tech-review

INO-SGD: Addressing Utility Imbalance under Individualized Differential Privacy

arXiv:2605.07930v1 Announce Type: cross Abstract: Differential privacy (DP) is widely employed in machine learning to protect confidential or sensitive training data from being revealed. As data owner

researcharxiv-cs-ai

InsHuman: Towards Natural and Identity-Preserving Human Insertion

arXiv:2605.07402v1 Announce Type: new Abstract: Human insertion aims to naturally place specific individuals into a target background. Although existing image editing models may have such ability, the

researcharxiv-cs-cv

Local Ai

Instruction Tuning Changes How Upstream State Conditions Late Readout: A Cross-Patching Diagnostic

arXiv:2605.07284v1 Announce Type: new Abstract: Recent interpretability work has identified model-internal handles on post-trained behavior, including refusal directions, assistant/persona axes, and s

local-aiarxiv-cs-lg

Integrating Causal DAGs in Deep RL: Activating Minimal Markovian States with Multi-Order Exposure

arXiv:2605.07057v1 Announce Type: new Abstract: Online reinforcement learning (RL) relies on the Markov property for guaranteed performance, but real-world applications often lack well-defined states

applicationsarxiv-cs-lg

Intelligent Truck Matching in Full Truckload Shipments using Ping2Hex approach

arXiv:2605.07733v1 Announce Type: cross Abstract: Accurate truck-to-shipment matching using GPS data is foundational for full truckload supply chain visibility, enabling real-time tracking and accurat

applicationsarxiv-cs-ai

Intent-Driven Semantic ID Generation for Grounded Conversational News Recommendation

model-releasesarxiv-cs-cl

arXiv:2605.07613v1 Announce Type: new Abstract: Conversational news recommendation requires grounding each suggestion in a rapidly evolving article corpus while addressing implicit user intents that l

IntentGrasp: A Comprehensive Benchmark for Intent Understanding

arXiv:2605.06832v1 Announce Type: cross Abstract: Accurately understanding the intent behind speech, conversation, and writing is crucial to the development of helpful Large Language Model (LLM) assis

Intention assimilation control for accurate tracking with variable impedance in teleoperation

arXiv:2605.07037v1 Announce Type: new Abstract: Robot systems for teleoperation commonly use a spring-like force pulling the follower robot towards the leader's position to track their movements. With

safetyarxiv-cs-ro

Interactive Jensen–Shannon Divergence Visualisation [P]

researchr-machinelearning

Jensen-Shannon divergence is a method of measuring the similarity between two probability distributions. It is based on the Kullback-Leibler divergence, with the notable difference that it is symmetri

Interactive Trajectory Planning with Learning-based Distributionally Robust Model Predictive Control and Markov Systems

arXiv:2605.07768v1 Announce Type: cross Abstract: We investigate interactive trajectory planning subject to uncertainty in the decisions of surrounding agents. To control the ego-agent, we aim to firs

agentsarxiv-cs-lg