Search: “papers”

Interesting new paper from Alexia Jolicoeur-Martineau (of Tiny Recursive Model fame) and collaborators. They seem to be able to replace quadratic attention with sliding window attention + attention si

// Your LLM judge disagrees with the experts // LLM Judges can be tricky to build. Here is an interesting showcasing why: There propose a reference-full benchmark of hundreds of complete human-to-huma

// Memory is what breaks long-horizon agents // It's undeniable how important memory/recall is for long-horizon tasks. If you are building for long-horizon tasks, this is a great read. (bookmark it) T

arXiv:2608.26548v1 Announce Type: cross Abstract: This paper considers a stationary camera calibration problem, which estimates the camera orientation angles yaw, pitch and roll, using a drone traject

// Automata from agent traces // How much of your agent's behavior comes from the model, and how much from the harness you wrapped around it? New work collapses an entire corpus of agent traces into a

arXiv:2404.11754v4 Announce Type: replace Abstract: This paper focuses on reducing the communication cost of federated learning by exploring generalization bounds and representation learning. We first

arXiv:2608.25135v1 Announce Type: new Abstract: This paper presents a novel method that extends targetless LiDAR-IMU calibration for ground vehicles to non- flat environments. Calibration typically ne

arXiv:2608.25182v1 Announce Type: cross Abstract: In this paper, we study alternating regret in online convex optimization (OCO), motivated by the success of alternating learning dynamics in two-playe

arXiv:2608.24559v1 Announce Type: cross Abstract: Despite the critical role of grey literature in scholarly communication, artefacts such as Calls for Papers (CfPs) remain largely isolated from modern

Impressive work from Alibaba. (bookmark it) If you build long-running agents and keep rewriting your memory schema, take a look at this approach. It basically treats agent context management as a prog

// There Is No Neutral Harness // Great work discussing some of the issues in harness evaluation. Twelve open-weight models answer the same 3,679 items from ARC, HellaSwag, MMLU, and TruthfulQA under

arXiv:2608.20420v1 Announce Type: new Abstract: This paper develops a phenomenology-first approach to artificial consciousness by reframing consciousness as the subjective experience enacted through a

arXiv:2606.13892v2 Announce Type: replace-cross Abstract: The intersection of crypto x AI is spawning papers, products, online posts, and companies. All the surrounding buzz, though, obscures what exa

Interesting new approach to enable memory in long-running agents. Weighted Memory Tree organizes execution into tasks, subtasks, and actions, then gives every memory a retention score that moves. Even

This is one of the most useful writeups I have seen on keeping an LLM judge effective in production. (bookmark it) Netflix runs judges over hundreds of thousands of show-level recommendation explanati

If you maintain an AGENTS.md or a CLAUDE.md, this one is worth your time. (bookmark it) Researchers traced 94K development events across 557 agentic coding sessions, plus 690K file-level change record

This is one of the most effective ways to improve your agentic workflows. If you are building computer-use agents, this one is worth your time. Task Model Induction takes a raw recording of someone wo

Impressive research from Google on building better environments for agents. Training environments for agents are hand-built and go stale. The agent improves, the environment does not, and it's not abl

arXiv:2511.03618v2 Announce Type: replace Abstract: In this paper, we formalize the almost sure convergence of Q-learning and linear temporal difference (TD) learning with Markovian samples using the

arXiv:2608.19210v1 Announce Type: cross Abstract: This paper focuses on the implementation of a novel supervised Machine Learning model for estimating helicopter weight during takeoff, utilizing exten

arXiv:2608.19230v1 Announce Type: cross Abstract: As language models move from drafting prose to running literature-search agents with tool calls, fabricated references are becoming easier to catch an

arXiv:2509.04100v3 Announce Type: replace Abstract: This paper explores the combination of Reinforcement Learning (RL) and search-based path planners to speed up the optimization of flight paths for a

arXiv:2608.18079v1 Announce Type: new Abstract: Game world modeling (GWM) and reinforcement learning (RL) are often confounded because research papers rarely quantify how difficult the underlying tran

arXiv:2608.18431v1 Announce Type: cross Abstract: This paper develops a computational framework to optimize the process parameters such that the bond quality between extruded polymer filaments is maxi

arXiv:2608.17244v1 Announce Type: cross Abstract: This paper addresses the limitations of Gaussian distribution assumptions in statistical sparse learning, particularly in modeling correlated and hete

Does your context compactor actually save anything? If you built or tuned one, this one is worth your time. (bookmark it) Task completion is the standard way to validate compression, and it hides the

arXiv:2608.16492v1 Announce Type: cross Abstract: This paper studies the regret analysis for parallel Gaussian process (GP) bandit optimization. The known regret upper bounds for the widely used GP ba

arXiv:2608.14942v1 Announce Type: cross Abstract: This paper presents the first known empirical investigation of annotator and reviewer performance across multi-source remotely sensed imagery, evaluat

arXiv:2604.03491v2 Announce Type: replace-cross Abstract: This paper proposes a method for estimating a surface that contains a given set of points from noisy measurements. More precisely, by assuming

arXiv:2608.14638v1 Announce Type: new Abstract: In this paper we study autoencoders, a special class of deep neural nets (DNNs) whose performance can be characterized via their fixed points. This pers

arXiv:2608.15641v1 Announce Type: new Abstract: This paper evaluates Wiktionary as an ethically crowdsourced lexicon for English dialects. We took a two-phase approach, providing an in-depth descripti

arXiv:2608.14843v1 Announce Type: cross Abstract: As authorship attribution systems are increasingly deployed to detect ghostwritten and AI-generated papers, their errors can support accusations again

Original Article - https://x.com/p_nawrot/status/2089315591010079034 I've spent the last few years working on efficient attention and KV Cache Compression. I've read many papers, dug deep into referen

arXiv:2204.13805v5 Announce Type: replace-cross Abstract: Gender gaps in how scientific work is evaluated are well documented, but their sources remain debated. We ask whether an overlooked factor---t

Friday's big release was Qwen 3.8 27B, an Apache 2 licensed 27B parameter vision-capable LLM from Alibaba's Qwen research lab. I've been looking forward to this one: 27B is an excellent size for runni

Interesting new research from IBM. If you pick models from benchmark deltas, some of that delta belongs to the phrasing rather than the model. BenchDrift generates meaning-preserving variations of ben

arXiv:2608.13560v1 Announce Type: cross Abstract: Transforming multimodal sources into condensed and structured media outputs can be fundamentally conceptualized as a long-horizon agentic process cent

arXiv:2608.12912v1 Announce Type: new Abstract: This paper considers the overestimation bias problem of Q-learning in the setting of a large action space, for the purpose of relieving the bottleneck o

arXiv:2608.12352v1 Announce Type: cross Abstract: AI governance frameworks can be known, used, and implemented in form without becoming governance in practice. This paper examines that problem through

arXiv:2608.11230v1 Announce Type: new Abstract: This paper introduces the edge-based contiguous p-median (ECpM) problem to partition the roads in a network into a given number of compact and contiguou

arXiv:2608.11415v1 Announce Type: cross Abstract: Large language models are being proposed as agents in scientific workflows, in domains where no downstream verifier exists. Such deployment assumes th

Four small architecture decisions can cost up to 47% of a model's long-context performance. New research from Ai2, Carnegie Mellon, and the University of Washington isolates them. Normalization, GQA,

arXiv:2608.11171v1 Announce Type: cross Abstract: The Workshop on Trustworthy Natural Language Processing (TrustNLP), co-located with major ACL conferences since 2021, has grown from 8 proceedings pap

Hey Folks, I've been making quants for a while - recently I took a short break to get into hardcore research (submitted my first EMNLP paper during it!). Along the way, I built up a little arsenal of

arXiv:2608.08882v1 Announce Type: cross Abstract: AI tools that help people judge online claims are usually evaluated while the tool is present. This paper asks a different question: after using such

arXiv:2601.17108v3 Announce Type: replace-cross Abstract: This paper proposes a hybrid Mamba-attention neural architecture to achieve improved channel estimation for orthogonal frequency-division mult