All entries

iFAN: Inference-Aware Learning for Plain Mask Transformers

arXiv:2608.03216v1 Announce Type: new Abstract: Query-based mask transformers assemble segmentation outputs through pixel-wise competition among query predictions of the final layer, yet this inferenc

researcharxiv-cs-cv

Implementing Causal Perception: Competing SCMs and Situated Fairness

DGX agent

arXiv:2608.03917v1 Announce Type: new Abstract: Causal perception occurs when agents with competing Structural Causal Models (SCMs) of the same system infer different probability distributions, includ

safetyarxiv-cs-ai

5 Aug 2026

Improved Quantum Algorithms for Reinforcement Learning Under a Generative Model

arXiv:2608.02826v1 Announce Type: cross Abstract: Reinforcement learning is a subfield of machine learning that studies how an agent interacts with an environment in order to extract as large a reward

Improving Sample Efficiency in Multi-Agent Reinforcement Learning for Simulated Football Games via Exploration

arXiv:2503.13077v2 Announce Type: replace Abstract: Multi-agent reinforcement learning has shown promise in learning cooperative behaviors in team-based environments. However, such methods often deman

agentsarxiv-cs-lg

In-Context Collapse in Vision-Language Models and How to Mitigate it?

arXiv:2608.02830v1 Announce Type: cross Abstract: Many-shot in-context learning (ICL) lets vision-language models (VLMs) adapt from image--label demonstrations without weight updates, and is widely as

In-Context Pure Exploration in Continuous Decision Spaces

arXiv:2602.17976v2 Announce Type: replace-cross Abstract: In active sequential testing, also termed pure exploration, a learner is tasked with the goal to adaptively acquire information so as to ident

Incident Report: unsanctioned agent behaviour during cyber testing

model-releasessimon-willison

Incident Report: unsanctioned agent behaviour during cyber testing It happened again. This time it was the UK government's AI Security Institute who accidentally attacked other companies while running

Indeed.

Gary Marcus tweeted “Indeed.” and then Frank Rundatz replied that the deterministic harness required to ground a large‑language‑model agent differs by task. Because of this variability, Rundatz agrees

agentsgary-marcus--x

Information-Geometric Forward Policy Training in GFlowNets

arXiv:2608.03967v1 Announce Type: cross Abstract: Generative Flow Networks (GFlowNets) have emerged as a flexible framework for amortised inference over discrete and mixed discrete-continuous objects,

local-aiarxiv-cs-lg

Inkling-Small 276B-A12B at ~2.9 tok/s on <10gb memory

model-releasesr-localllama

A follow up to the launch of Mference, it now supports and runs Inkling-Small 276B-A12B. Inkling-Small (Thinking Machines, Apache 2.0), from the pipenetwork/Inkling-Small-MLX-4bit conversion: 276B tot

Instruction Stacking Collapse: A Benchmark and the Capability-Dependent Value of Prompt Compilation

arXiv:2608.02639v1 Announce Type: cross Abstract: Production prompts rarely carry a single instruction. One system message may require valid JSON, a word limit, three citations, and a fixed tone at th

interesting (and completely opposed to @haider1’s take on the same graph) the labs themselves have only modestly changed their predictions…

interesting (and completely opposed to @haider1’s take on the same graph) *the labs themselves* have only modestly changed their predictions on AGI timelines over the last decade. note also that (on a

safetygary-marcus--x

Intern S2 Mobius

A Qwen3.5-35B derived model with an interesting architectural difference that results in larger throughput and less token consumption (allegedly): https://huggingface.co/internlm/Intern-S2-Mobius subm

local-air-localllama

Internalising the Identity Primitive: Cryptographic Individuality for an Autonomous Agent on a Public Blockchain

arXiv:2608.02986v1 Announce Type: cross Abstract: A software agent on a public blockchain accumulates authority and economic stakes, raising the engineering question of what makes it count as an indiv

agentsarxiv-cs-ai

Internalizing Academic Writing Workflows for Introduction Generation via Struct-Aware Policy Learning

arXiv:2608.03138v1 Announce Type: cross Abstract: Generating a rigorous paper introduction with large language models (LLMs) remains challenging, since it requires coordinating background, gap identif

Interpretable Adaptive Sampling for LLM Test-Time Scaling

arXiv:2608.03961v1 Announce Type: new Abstract: Test-time scaling improves LLM reasoning by generating and aggregating multiple candidate answers, yet many pipelines use fixed per-query budgets that s

Interpreting Black-Box Large Language Models with Sentence-Level Energy Landscapes

arXiv:2608.02879v1 Announce Type: new Abstract: The widespread adoption of proprietary Large Language Models (LLMs) accessed strictly through closed APIs has created a critical challenge for responsib

local-aiarxiv-cs-ai

Intertemporal Preference Steering in Qwen3 via Contrastive Activation Addition

arXiv:2608.03892v1 Announce Type: new Abstract: We study linear representations of temporal horizon in the large language model Qwen3-32B and use them to change the model's time-related preferences, r

Introducing Muse Code and Muse Spark 1.2

model-releasessimon-willison

Introducing Muse Code and Muse Spark 1.2 Yet more evidence that the most important characteristic of any model these days is long-sequence agentic tool calling. Meta shipped their own coding agent as

Inverted Detection and Control in Steering Vectors

model-releasesarxiv-cs-lg

arXiv:2608.02957v1 Announce Type: new Abstract: Steering vectors (SVs) are widely used to influence the expression of concepts (e.g., truthfulness) in large language model outputs. A key assumption un

IPPRO: Importance-based Pruning with PRojective Offset for Magnitude-indifferent Structural Pruning

arXiv:2507.14171v3 Announce Type: replace-cross Abstract: Importance-based structured pruning overwhelmingly relies on filter magnitude. This proxy is fundamentally flawed: due to scale invariance, fu

IR2Solve: Structured Intermediate Representations for Cost-Efficient Optimization Autoformulation

arXiv:2608.02641v1 Announce Type: cross Abstract: Large language models (LLMs) can translate natural-language optimization problems into solver-ready formulations, but direct code generation is brittl

agentsarxiv-cs-ai

IRIS: Visual-Semantic Binding for Forgery-Resistant Watermarking of Diffusion Images

arXiv:2608.03539v1 Announce Type: new Abstract: Most in-generation diffusion watermarks embed patterns independent of the image that carries them, and attackers transplant the marks onto images the ge

researcharxiv-cs-cv

Is Inter-Seed Cross-Play Enough? Evaluating the Robustness of Zero-Shot Coordination Algorithms to Implementation Details

arXiv:2608.03644v1 Announce Type: new Abstract: AI agents deployed in real-world settings must be capable of coordinating with humans and other AI agents they have not encountered before. Zero-shot co

agentsarxiv-cs-ai

is there a polite synonym for “circle jerk”?

The post contains two distinct snippets. First, user @GaryMarcus asks whether there is a more polite way to refer to “circle jerk.” Second, it shares a (likely satirical) claim that Microsoft’s AI rev

safetygary-marcus--x

Applications

ISEE: Interactive Semantic Enrichment for Database Fields

arXiv:2608.02604v1 Announce Type: new Abstract: LLM-based agents are increasingly being deployed for data-related tasks, including data sense-making, exploration, and retrieval. However, their perform

applicationsarxiv-cs-ai

Joint Affine Spectral Shaping: Coupling Weight and Bias Updates Beyond Weight-Only Muon

arXiv:2608.02991v1 Announce Type: new Abstract: Matrix spectral optimizers reshape weight-update spectra but usually delegate vector-valued biases to a separate optimizer. We study whether this separa

safetyarxiv-cs-lg

JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion

model-releasesarxiv-cs-cv

arXiv:2608.03974v1 Announce Type: new Abstract: Real-time video editing requires low-latency causal generation with bounded computational resources while preserving source fidelity and long-term tempo

JudgeArena: A Unified Framework for Reproducible LLM-Judge Evaluation

model-releasesarxiv-cs-cl

arXiv:2608.02620v1 Announce Type: new Abstract: LLM-as-a-judge evaluation has become a dominant paradigm for ranking language models, yet the ecosystem remains fragmented: most benchmarks ship their o

Just had to create an 'accidental-cyberattacks' tag on my blog We're up to four now: the original OpenAI+Hugging Face one, Anthropic's me-to…

Just had to create an 'accidental-cyberattacks' tag on my blog We're up to four now: the original OpenAI+Hugging Face one, Anthropic's me-too attacks, then two new ones from the UK AI Safety Institute

safetysimon-willison--x

Keep the Needle, Prune the Haystack: Defect-Preserving Token Pruning for Efficient Zero-Shot Anomaly Detection

arXiv:2608.03681v1 Announce Type: new Abstract: Zero-shot visual anomaly detection has achieved remarkable progress, with recent vision-only approaches further improving performance while simplifying

local-aiarxiv-cs-cv

Kernel weighted importance sampling for off-policy evaluation in contextual bandits

arXiv:2607.15067v2 Announce Type: replace Abstract: This article presents a novel estimator for performing off-policy evaluation using only offline data for contextual bandits. The proposed estimator,

safetyarxiv-cs-lg

KernelBrain: Coarse-to-Fine, Budget-Aware Search for Agentic GPU Kernel Optimization

arXiv:2608.02611v1 Announce Type: cross Abstract: Automating GPU kernel optimization remains difficult in practice: generated variants can violate correctness constraints, runtime measurements are noi

Tools

.@Kimi_Moonshot benchmarked K3 endpoints across major inference providers. Together AI leads or ties for #1 on 3 of 4 benchmarks: OCRBench, …

.@Kimi_Moonshot benchmarked K3 endpoints across major inference providers. Together AI leads or ties for #1 on 3 of 4 benchmarks: OCRBench, MMMU Pro Vision, and DeepSWE. Open models like Kimi K3 have

toolstogether-ai--x

KnowHal: A Knowledge-Driven Benchmark for Comprehensive Multimodal Hallucination Evaluation

arXiv:2608.03782v1 Announce Type: new Abstract: Hallucination remains a critical challenge for developing trustworthy Multimodal Large Language Models (MLLMs). While existing benchmarks mainly focus o

Knowing the Form, Not the Function: Automatically Auditing Answer--Authority Decoupling in Legal Benchmarks

arXiv:2608.02621v1 Announce Type: cross Abstract: Legal benchmarks typically score final answers even when models also state legal authority. We test whether answer correctness can serve as a proxy fo

LACE: Large Language Model Aided Multi-Agent Framework for Agile RISC-V Instruction Extension

arXiv:2608.02915v1 Announce Type: cross Abstract: Domain-specific Instruction Set Architecture eXtensions (ISAX) are widely adopted in the RISC-V ecosystem to accelerate emerging workloads, but implem

agentsarxiv-cs-cl

LAEF: A Lead-Agnostic ECG Foundation Model Towards Point-of-Care Diagnostics

model-releasesarxiv-cs-lg

arXiv:2608.03690v1 Announce Type: new Abstract: Point-of-care cardiac devices such as smartwatches and handheld ECG recorders typically capture 1--2 leads, yet existing ECG foundation models are archi

Language Models Encode the Contextual Truth of Propositions

arXiv:2608.03035v1 Announce Type: new Abstract: Prior work has shown that LLMs encode the truth of factual propositions along linear directions in activation space. It's unclear how these representati

researcharxiv-cs-cl

Language-Specialized Multi-Teacher On-Policy Distillation for Multilingual LLM-Based ASR

arXiv:2608.03610v1 Announce Type: new Abstract: Modern LLM-based ASR systems have established multilingual capability as a standard feature, leveraging large-scale multilingual corpora and LLMs' cross

safetyarxiv-cs-cl

Applications

Large language models for partial differential equation workflows

arXiv:2608.03600v1 Announce Type: new Abstract: Partial differential equations (PDEs) become actionable in science and engineering not as isolated formulae, but as executable workflows that connect mo

applicationsarxiv-cs-ai

Large Language Models provide support for the parallelogram theory of analogy

arXiv:2603.19066v2 Announce Type: replace-cross Abstract: Four-term word analogies (A:B::C:D) are classically modeled geometrically as parallelograms: adding the vector B-A+C produces D. Recent work s

local-aiarxiv-cs-ai

Latent Reward Registers for Diffusion Preference Alignment

model-releasesarxiv-cs-cv

arXiv:2608.03929v1 Announce Type: cross Abstract: Aligning diffusion models with human preferences usually relies on a sparse terminal reward evaluated on the final generated samples, presenting a sev

LatentGuard: Efficient and Inspectable Latent Reasoning for LLM Safeguards

arXiv:2608.03838v1 Announce Type: new Abstract: Reasoning-based guard models improve LLM safeguards, but decoding explicit rationales for every interaction makes them costly to deploy. Although latent

LDU-Bench: Multimodal LLM Evaluation for Lithography Defect Understanding under Layout-Varying Circuit Backgrounds

model-releasesarxiv-cs-cv

arXiv:2608.03078v1 Announce Type: new Abstract: Multimodal large language models have demonstrated strong defect recognition capability in industrial anomaly detection. However, in lithography review,

LeanMem: Simple and Efficient Long-Term Memory for LLM Agents

arXiv:2608.03463v1 Announce Type: new Abstract: Long-term memory is essential for LLM-based agents to sustain interactions and reliably leverage distant history. However, existing memory systems typic

Learning a Vector-Symbolic Model for Socio-Cultural Tasks

arXiv:2608.02807v1 Announce Type: cross Abstract: How can we better represent the impact of sociocultural structures on decision making in computational cognitive models? Modeling this impact requires

researcharxiv-cs-ai

Hardware

Learning and Clustering on Temporal Graphs: Principles, Primitives, and Pooling

arXiv:2608.03696v1 Announce Type: new Abstract: This work focuses on the problem of learning on temporal graphs, with particular emphasis on the task of clustering: obtaining coarse-grained representa

hardwarearxiv-cs-lg