research

The Geometry of Sequential Learning: Lie-Bracket Prediction of Transfer Order

arXiv:2606.24993v1 Announce Type: new Abstract: Sequential learning is order-dependent: from Pile-style next-token domain adaptation to instruction-SFT and DPO, N candidate sources induce N! possible

Research

The Inference-Compute Frontier and a Latency-Efficient Architecture for Limit Order Book Prediction

DGX agent

arXiv:2606.25986v1 Announce Type: new Abstract: We study whether a scaling-law-style inference-compute frontier appears in limit order book prediction. Using FI-2010 and a suite of models ranging from

researcharxiv-cs-lg

25 Jun 2026

The Interplay of Harness Design and Post-Training in LLM Agents

arXiv:2606.25447v1 Announce Type: cross Abstract: Tool-integrated LLM agents are often wrapped within a harness: the scaffolding that determines which tools are exposed, how they are described, and wh

The true measure of a software engineer isn't their ability to write clever code. It's their ability to ruthlessly protect the codebase from…

researchfrancois-chollet--x

Francois Chollet argues that a software engineer's true value lies not in writing complex or clever code, but in their ability to protect the codebase from degradation, technical debt, and poor practi

Towards a Dynamic and Fixed-budget Memory Bank for Efficient Streaming Video Understanding

arXiv:2606.25658v1 Announce Type: new Abstract: Currently, streaming video understanding is still a daunting task for existing multimodal large language models (MLLMs). Its difficulties not only lie i

Towards Structuring an Arabic-English Machine-Readable Dictionary Using Parsing Expression Grammars

arXiv:2606.25231v1 Announce Type: new Abstract: Dictionaries are rich sources of lexical information about words that is required for many applications of natural language processing and human languag

Tracing Target Answers in Poisoned Retrieval Corpora via Token Influence Attribution

arXiv:2606.25721v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems are vulnerable to corpus poisoning attacks that manipulate model outputs through malicious retrieved docu

Training Dynamics of Neural Software Defect Predictors under Coupled Data-Quality Issues

arXiv:2606.24968v1 Announce Type: new Abstract: Context: Software defect prediction supports maintenance decisions such as testing prioritization, release-risk assessment, and quality monitoring. Howe

Transferable Attack against Face Swapping in an Extended Space

arXiv:2606.25376v1 Announce Type: new Abstract: Although deep Face Swapping (FS) models may benefit the entertainment industry, they pose severe threats to privacy and security. Existing protections,

TRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memory

arXiv:2606.25161v1 Announce Type: new Abstract: Large language model (LLM) agents rely on long-term memory to support extended interactions and personalized assistance beyond finite context windows. E

TryOnCrafter: Unleashing Camera Trajectories for Realistic Video Virtual Try-on via a Renderable 4D Try-on Proxy

arXiv:2606.26092v1 Announce Type: new Abstract: While Video Virtual Try-on (VVT) has achieved remarkable progress in synthesizing realistic garment overlays on dynamic subjects, existing paradigms rem

Two Stages of Folding: Convergent Mechanisms in AI Protein Folding Trunks

arXiv:2602.06020v3 Announce Type: replace Abstract: How do protein structure prediction models fold proteins? We investigate this question through causal interventions on the folding trunks of ESMFold

UC-Search: Risk-Aware Test-Time Search for Delayed Constrained Time-Series Control

arXiv:2606.25274v1 Announce Type: new Abstract: Time-series models are usually scored as forecasters, yet deployed systems often require delayed decisions under uncertainty and hard feasibility constr

Understanding the brain with AI-driven explanations and experiments

researchmicrosoft-research

Researchers introduce generative causal testing, which translates black box models into clear hypotheses and verifies them in the scanner, revealing what specific brain regions respond to in language.

Variable Bound Tightening for Nash Equilibrium Computation in Multiplayer Imperfect-Information Games

arXiv:2606.25997v1 Announce Type: cross Abstract: There has been significant recent progress in algorithms for approximation of Nash equilibrium in large two-player zero-sum imperfect-information game

Variational Autoencoder Layer

arXiv:2606.25900v1 Announce Type: new Abstract: Variational Autoencoders (VAEs) belong to a family of autoencoders with probabilistic properties, making them well suited for generating data by produci

Variational Inference via Entropic Transport Descent

arXiv:2606.25265v1 Announce Type: new Abstract: Particle-based variational inference (ParVI) methods approximate an intractable target distribution by evolving an ensemble of interacting samples. Exis

Velocity Prediction in Automatic Guitar Transcription

arXiv:2606.24912v1 Announce Type: cross Abstract: Automatic Music Transcription (AMT) models have achieved a high level of success in polyphonic transcription of various instruments. Velocity, typical

VENI: Variational Encoder for Natural Illumination

arXiv:2601.14079v2 Announce Type: replace Abstract: Inverse rendering is an ill-posed problem, but priors such as illumination priors can help simplify it. Existing work either disregards the spherica

Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models

arXiv:2606.25041v1 Announce Type: new Abstract: We present Wan-Streamer, a native-streaming, end-to-end interactive foundation model designed from the ground up for real-time, low-latency, full-duplex

WaveForward: An Omnidirectional Passive Wheeled Quadruped Robot with Casters

arXiv:2606.25299v1 Announce Type: new Abstract: Wheeled-legged robots possess both agile mobility for traversing complex terrains and high efficiency, making them suitable for long-distance transporta

researcharxiv-cs-ro

Weave of Formal Thought

arXiv:2606.25987v1 Announce Type: new Abstract: Large language models (LLMs) attain remarkable surface fluency on code, yet they neither formally guarantee the syntactic validity of their output nor l

Weight Space Representation Learning via Neural Field Adaptation

arXiv:2512.01759v3 Announce Type: replace Abstract: We investigate the potential of weights to serve as effective representations, focusing on neural fields. Our key insight is that constraining the o

What Europe’s heat wave means for the power grid

It’s been hard to look away from headlines about the European heat wave this week. Temperatures are breaking records across the continent, and the weather is threatening lives, shutting down schools,

researchmit-tech-review

What is IBM's nanostack chip architecture?

IBM's nanostack is a chip architecture that stacks multiple layers of transistors vertically to increase transistor density and computing power within a smaller physical footprint. This 3D approach en

researchibm-research

When Certainty Is an Artifact: Keyword Lexicon Blindness and the (Mis)Measurement of Rhetorical Stance

arXiv:2606.26062v1 Announce Type: new Abstract: Can a statistically significant, large-effect-size finding in computational social science be entirely an artifact of the measurement instrument? We pre

When the cost of execution drops, the value of taste, strategy, and architectural vision skyrockets. Previously, you were spending most of y…

researchfrancois-chollet--x

When the cost of execution drops, the value of taste, strategy, and architectural vision skyrockets. Previously, you were spending most of your cognitive budget on the micro. Now you are free to focus

Why Do Accumulated Transformations Extrapolate?

arXiv:2606.24975v1 Announce Type: cross Abstract: PaTH Attention showed that replacing RoPE's position-indexed rotations with accumulated data-dependent Householder reflections yields strong length ex

Why Pool When You Can Flow? Active Learning with GFlowNets

arXiv:2509.00704v2 Announce Type: replace Abstract: The scalability of pool-based active learning is limited by the computational cost of evaluating large unlabeled datasets, a challenge that is parti

You can now hatch & share your own pets w/ Hermes @NousResearch

Nous Research has introduced a feature that allows users to create and hatch their own digital pets within the Hermes platform, with the ability to share these pets with others. This update likely enh

researchnous-research--x

A Dual Edge Spatial Jacobian Image Graph for Interpretable Diabetic Retinopathy Grading

arXiv:2606.24168v1 Announce Type: cross Abstract: Automated diabetic retinopathy (DR) grading from colour fundus photographs can achieve strong predictive performance, but clinical interpretation requ

A Fast and Effective Method for Euclidean Anticlustering: The Assignment-Based-Anticlustering Algorithm

arXiv:2601.06351v2 Announce Type: replace Abstract: Anticlustering is an NP-hard combinatorial optimization problem that consists of partitioning a set of objects into equal-sized groups called anticl

A new playbook for quantum optimization benchmarking

IBM Research presents a framework for benchmarking quantum optimization algorithms, addressing the need for standardized methods to evaluate quantum computing performance on optimization problems. The

researchibm-research

A novel Framework for Open-Vocabulary Multi-Object Recognition using CLIP

arXiv:2603.05962v2 Announce Type: replace Abstract: To address the limitations of existing open-vocabulary object recognition methods, including high system complexity, substantial training costs, and

A Survey on Federated Causal Discovery and Inference

arXiv:2606.23741v1 Announce Type: cross Abstract: Causal reasoning, which encompasses the discovery of causal structures and the inference of causal effects, is fundamental to data-driven decision mak

A Unified Framework for Runtime Verification and Model-Based Diagnosis in LOLA

arXiv:2606.23720v1 Announce Type: cross Abstract: We present an integrated framework that unifies runtime verification and model-based diagnosis within the stream specification language LOLA. By encod

Accelerating Multimodal Large Language Models with Prior-Corrected Token Reduction

arXiv:2606.24156v1 Announce Type: new Abstract: Visual token reduction has emerged as an effective strategy for accelerating Multimodal Large Language Models (MLLMs). Many existing methods prune token

Adaptive Hebbian Memory Routing in Vision Transformers for Few-Shot Learning

arXiv:2606.24756v1 Announce Type: new Abstract: Few-shot image recognition requires models to adapt to new classes from a small labeled support set. Hebbian fast-weight memory can provide temporary as

Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods

arXiv:2606.24484v1 Announce Type: new Abstract: WordArt (artistic text) features highly customized fonts, textures, and layouts, making WordArt-oriented scene TExt Recognition (WATER) substantially mo

Adversarial dynamical systems characterize when data-driven learning succeeds or fails

arXiv:2407.06312v2 Announce Type: replace-cross Abstract: Many systems resist analytical modeling, making data-driven inference of dynamics important. Yet data-driven methods can fail to converge or g

AerialFusionMapNet: Online HD Map Construction with Aerial-Onboard BEV Fusion

arXiv:2606.24784v1 Announce Type: new Abstract: High-resolution aerial imagery has recently emerged as a complementary modality for automated driving perception and has shown potential to improve bird

AI Fiction in the Wild

arXiv:2606.22748v2 Announce Type: replace-cross Abstract: Some professional authors are beginning to use AI tools to help produce their fiction writing. Are readers using AI to generate fiction, too?

All challenges big and small

When I was 18, I skipped my high school graduation and headed to Kuwait. It was 1991, the first Gulf War had just ended, and the country was in complete chaos. There was little to no electricity, asid

researchmit-tech-review

An Agnostic Machine Learning Model of Photosynthetic Habitability

arXiv:2606.24458v1 Announce Type: cross Abstract: The search for exoplanet biosignatures is guided by whether planetary environments can sustain photosynthesis. As such, the Photosynthetic Habitable Z

Aspect-Based Sentiment Evolution and its Correlation with Review Rounds in Multi-Round Peer Reviews: A Deep Learning Approach

arXiv:2606.24188v1 Announce Type: new Abstract: Mining sentiment information from the textual content of peer review comments offers valuable insights into the scientific evaluation process. However,

Automated Residual Plot Assessment With the R Package autovi and the Shiny Application autovi.web

arXiv:2606.24236v1 Announce Type: cross Abstract: Visual assessment of residual plots is a common approach for diagnosing linear models, but it relies on manual evaluation, which does not scale well a

Automatic Part-of-Speech Tagging of Arabic-English Dictionary Senses through WordNet

arXiv:2606.24359v1 Announce Type: new Abstract: This paper proposed an algorithm for part-of-speech (POS) tagging senses of a bilingual dictionary. The algorithm is applied on the Al-Mawrid Arabic-Eng

AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression

arXiv:2606.24286v1 Announce Type: new Abstract: Multimodal Large Language Models have achieved remarkable progress in short-form audio-video understanding, yet long-form audio-video comprehension rema