AIPULSE
Live

Discover

Latest research papers and top Hacker News stories

Latest Papers24
1
ML

FETTUCCINE: Fast and efficient brain-to-text decoding on mobile devices

Recent advances in speech neuroprostheses have enabled new communication avenues for people who have lost the ability to speak due to neurological illness or injury. These systems can decode neural activity during attempted speech into text by relying on language priors to achieve high decoding accuracy. This performance currently comes at the cost of using a compute-intensive language modeling stack, presenting a major bottleneck for real-world use. Further, current language models incur highly variable and disruptive inference latencies, limiting communication throughput and preventing users

Jonathan D. McCart, Pranav I. Deevi, Mehdi Azabou·4 days ago
2
RoboticsMLRobotics

Training Reasoning Models in Simulation to Natively Use Real Robots

Robot-use agents (RUAs) have emerged as a promising approach to general-purpose robot control. However, strong performance has so far been achieved only by frontier proprietary models such as GPT-6 Astra and Claude Fable 5.2, whereas open-weight models remain substantially less capable. We show that an open-weight 27B reasoning model can be trained to use real robots natively through reinforcement learning, entirely in simulation and without demonstrations. Like a computer-use agent (CUA), the model observes the environment, reasons in a chain of thought, and generates the next end-effector po

Jiaming Tang, Zhuoyang Zhang, Junxian Guo·4 days ago
3
VisionMLVision

BAL: Bidirectional Autoregression in Latent Space for Learning Human Movement Representations

Learning semantically meaningful human movement representations from 3D pose sequences is essential for human behavior modeling. Existing self-supervised methods derive supervision from artificial assumptions, e.g., invariance to augmentation within a certain range or recoverability of masked regions at a certain temporal scale, introducing heuristic hyperparameters that make the learned semantics sensitive to their settings. We propose BAL, a self-supervised framework that instead exploits supervision intrinsic to human movement: the natural ordering structure of everyday behavior. BAL autore

Genki Kinoshita, Ko Nishino·4 days ago
4
MLAIML

WeightBench: Evaluating Language Models as Weight-Space Programmers

Recent work shows that large language models (LLMs) can operate directly on the parameters of other neural networks. They can read what a network was trained to do, fix a network that fails, and write working networks from scratch, all without gradient descent. This capability has been termed Weight-Space Programming (WSP). Exploring this new paradigm systematically requires a robust benchmark. We introduce WEIGHTBENCH, a benchmark that evaluates LLMs of increasing capability on 42 WSP tasks across five tracks: reading, fixing and writing weights, recognizing edits that are impossible, and dat

Aayush Marasini, Barsat Khadka, Nick Rahimi·4 days ago
5
AIAIcs.MA

Imitation Bootstrapped Multi-Agent Reinforcement Learning

Demonstrations are an effective way to accelerate single-agent reinforcement learning (RL), but extending this idea to multi-agent reinforcement learning (MARL) is non-trivial as it is difficult and often impossible for a single person to teleoperate multiple agents simultaneously. Round-Robin Behavior Cloning (R2BC) addresses this by letting a single demonstrator control one agent at a time while the others execute their current policies. However, the resulting imitation policies are limited by the quality of the demonstrations. We propose Imitation Bootstrapped Multi-Agent Reinforcement Lear

Tony H. Zhang, Connor Mattson, Daniel S. Brown·4 days ago
6
AIML

Elliptic Sampling: Optimal Interpolant Schedules for Gaussians and Beyond

Generative modeling based on stochastic interpolants requires specifying two key choices: an interpolant schedule bridging the initial and target distributions, and an efficient discretization of the resulting probability-flow ODE. In this work, we introduce a new framework for joint schedule/discretization design based on the analyticity properties of the (complexified) ODE trajectories, which in turn ensure good numerical behavior. Our formulation can be solved exactly via conformal mapping, yielding a natural family of variance-preserving elliptic schedules, parametrized by Jacobi elliptic

Cole Becker, Taylan Kargin, Kimia Hassibi·5 days ago
7
MLcs.IT

Why Finite Intelligence Works in an Infinite World: A Mathematical Theory

An information system often has to learn before it knows what it will be asked. A finite representation can succeed without recording an infinite environment in full when those asks share collective structure, rather than demand unrelated facts scattered arbitrarily across it. We formalize this phenomenon through future-task information, the minimum retained information needed to preserve decision value relative to the available evidence. A joint decision-regret state records posterior comparisons among actions for every permitted task. Under compactness assumptions, every retained representat

Mojtaba Soltanalian·5 days ago
8
AINLPML

ModHarness-RL: Recasting Harnesses as Learnable and Evolving Programs for Agentic RL

Agentic reinforcement learning (RL) increasingly relies on a harness, the scaffold around the model that decides what it sees of its own interaction and what guidance it receives. Most existing approaches train under a hand-written harness that stays fixed throughout. However, an effective harness depends on the domain, the data and the model, and keeps changing as the model trains. We introduce ModHarness-RL, which recasts the harness as programs that are learned from data and evolve as the model trains with RL. ModHarness-RL records the interaction as structured State, a set of typed blocks,

Zelin He, Siyu Zhu, Jacob Helwig·5 days ago
9
AIAI

Alignment by Socialization: Learning Tradeoffs Under Selection

Artificial intelligence (AI) agents are expected to complete tasks while following rules of conduct, but these objectives can conflict. We study how evolutionary selection shapes an agent's choices between them, and whether experience can make those choices reflect human judgments and withstand subsequent pressures. In our model, copies of an agent face a common uncertain reward state, and only those taking the rewarded action reproduce. We show that long-run growth is maximized when each action is taken as often as the environment rewards it. We compare three policies. A task-only policy thri

Thomas Brennan, Andrew W. Lo, Chaoyi Zhao·5 days ago
10
VisionMLVision

Understanding Contextual Bias in Agricultural CNNs Through Hidden-Neuron Concept Induction

Convolutional Neural Networks (CNNs) can classify images using background-dominated patches that contain little or none of the target object, showing that they exploit contextual information. Previous studies detected this behavior through classification accuracy but say little about what CNN hidden layers represent. We investigate whether Concept Induction can reveal interpretable visual properties associated with hidden-neuron activations on contextual image patches. Using five agricultural datasets with high, moderate, and low contextual bias, we analyze four CNN architectures at three netw

Abhilekha Dalal, Avishek Das, Samatha Ereshi Akkamahadevi·5 days ago
11
VisionMLVisioncs.IR

StreamEmbed: Real-Time Indexing from Pixels for Screenshot Retrieval

Screen history can serve as searchable visual memory for people and agents, but unlike an offline corpus, it must be encoded and indexed as each screenshot arrives. OCR-based indexing is fast but loses visual information; visual encoding takes over two seconds. Yet screens change incrementally: most pixels repeat within and across screenshots. This raises a question: do visual encoders need to recompute their representations from scratch for every new screenshot? We present StreamEmbed, a system for incremental visual embedding that exploits this redundancy. Guided solely by pixel differences,

Dayoon Ko, Yichuan Wang, Soyeong Jeong·5 days ago
12
AINLPAI

Can Mechanistic Interpretability Help Explain LLM Agent Failures? A Case Study on Web Element Hallucination

Mechanistic Interpretability (MI) has made significant progress in explaining the internal computations of Large Language Models (LLMs); however, these advances have yet to demonstrate comparable success in explaining the decision-making processes of LLM-based agents. This paper examines the challenges MI tools face when applied to realistic agentic failures. We focus on one such failure: web agents hallucinating actions that are not available on a website. We apply a series of mechanistic analyzes to Qwen2.5-7B-Instruct as it interacts with live websites. We find that a linear probe trained o

Mohamed Aghzal, Mor Geva, Gregory J. Stein·5 days ago
13
AINLPcs.IR

MeReader: An Offline, Privacy-Preserving, Progress-Aware AI Assistant for Narrative eBook Reading

This paper introduces MeReader, a privacy-preserving, offline and progress-aware AI assistant designed to function as a contextual companion for narrative reading on consumer hardware. Unlike conventional Large Language Model (LLM)-based systems that process documents/books online in an all-texts-at-once type of way, thereby risking narrative spoilers, MeReader confines both retrieval and generation to the reader's distinct position in the text. The system integrates a hybrid retrieval architecture, combining vector similarity, BM25, and summary embeddings, to ensure high fidelity to the reade

Mohammed Efaz, Udo Bub, Itilekha Podder·5 days ago
14
MLML

On numerical issues of divergences between nearly equal distributions

Barron et al. (2026) recently identified numerical issues in the softmax and soft cross-entropy loss. We show that similar issues are present in standard divergence operations between categorical distributions. This includes the forward and reverse Kullback-Leibler (KL) divergence and generalized Jensen-Shannon divergence (JSD), as well as Monte Carlo KL estimates and entropy. When the distributions are nearly equal, rounding and cancellation issues affect the forward and gradient computations. These issues can affect settings using divergences in optimization objectives, such as knowledge dis

Brandon Amos·5 days ago
15
MLML

Asymptotic Margins and Feature Confinement in Conic Classification Heads under Softmax Cross-Entropy

Classification heads built on conic functions give each class a bounded region of the feature space, and such regions are used to reject samples of unseen classes. We ask whether these regions also keep the features bounded when the head is trained with softmax cross-entropy. For a head whose class scores combine a linear term with a Euclidean norm, we first show that the region of each class is bounded by a quadric of revolution, whose eccentricity is the reciprocal of one learned ratio. We then attach to each class an asymptotic margin, which compares the growth of its score with the growth

Omer Nezih Gerek·5 days ago
16
AI

Agentic AI for Discovering Fault-Tolerant Quantum Circuits

Scaling quantum computing toward practical quantum advantage is currently limited by the efficiency of circuits that operate on information encoded by quantum error-correcting codes. The full stack of quantum computing encompasses several tasks: preparation of logical code states, implementation of logical gates, logical routines on encoded qubits, etc. Yet, these circuits are largely designed by hand for individual cases, with some recent works incorporating machine learning for certain aspects. We formulate this problem as agentic evolutionary program synthesis, wherein a large language mode

Aritra Lahiri, Florian Marquardt·5 days ago
17
AIAI

ARCHER: From Rationale Imitation to Executable Reasoning in Small Language Models

Small language models are attractive for local, low-cost, and privacy-sensitive deployment, but they remain unreliable on mathematical reasoning tasks that require decomposition, exact computation, tool use, and verification. We introduce \textbf{ARCHER}: \textbf{A}ction-trace \textbf{R}einforcement for \textbf{C}alculator-grounded \textbf{H}ierarchical \textbf{E}xecutable \textbf{R}easoning, a two-stage framework for training small language models (SLMs) to produce executable and auditable reasoning trajectories. In the first stage, ARCHER compiles free-form chain-of-thought rationales into t

Dhruv Dixit, Khushi Patel, Congcong Xu·5 days ago
18
AIcs.MA

TradeGauntlet: Evaluating Compliance Controls for Autonomous Trading Agents

Autonomous trading agents need controls that prevent problematic orders without making legitimate tasks impractical. We study this aspect of agentic compliance with TradeGauntlet, a replayable limit-order-book simulator that separates detection, prevention, and execution cost. In 1,680 simulated sessions with Claude Haiku 5.5 and Sonnet 5.5, all conduct alerts were self-matches. Gates eliminated those alerts by rejecting self-crossing orders, while the aggregate-gate condition reduced Sonnet's two-sided fills by about 15%. A conduct reminder reduced Sonnet's alert rate but reduced Haiku's fill

Sandip Nandi, Aishwarya Bose, Apurba Bose·5 days ago
19
NLPAIML

Interactive Program Induction with Language Model Priors

Program induction refers to the process in which a learner aims to recover a program from a few given input-output examples. This paradigm broadens programming access by letting users demonstrate the rule-based behavior they want to apply to unseen data, instead of having to implement it themselves. However, recovering a program from finite input-output examples is fundamentally ambiguous, as a finite set of input-output examples is theoretically consistent with infinitely many programs whose output diverges on unseen inputs. We view this problem from a Bayesian perspective, where, given a pri

Robin Shing Moon Chan, Ryan Cotterell·5 days ago
20
RoboticsAIRoboticscs.MA

From AI-Enabled Remote Patient Monitoring Toward Agentic Robotics: Embodiment, Governance, and Care Integration

AI-enabled remote patient monitoring is evolving beyond passive data collection toward agentic AI systems that interpret patient states, coordinate care, and initiate action across domestic and clinical settings. This structured scoping review finds that mature agentic care has not yet emerged: Most systems remain human led, while stronger decision-action coupling and embodied AI remain largely confined to prototypes and pilots. Healthcare robotics makes the transition from monitoring to action especially visible by translating AI-generated recommendations and decisions into speech, movement,

Ivana Ragusa, Lorenzo Guiducci, Filippo Cavallo·5 days ago
21
ML

Bregman geometry in regular exponential families: dual representations and relative smoothness

Regular exponential-family distributions are ubiquitous in statistics due to their appealing and convenient properties. Notably, they can be expressed in terms of Bregman divergences, revealing fundamental connections between statistics, convex analysis, and information geometry. However, this geometric structure has not been systematically exploited to characterize these distributions with respect to their expectation parametrization. Building on a projective characterization, we establish a general construction of equivalent dual Bregman representations, together with normalization and uniqu

Mame Diarra Fall, Éric Barat, Nicolas Dobigeon·5 days ago
22
MLcs.SE

Evaluating Feedback-Driven Black-Box Processes via Stochastic Modeling and Simulation

We study feedback-driven black-box processes across software engineering and machine learning. These processes are inherently sequential: policies generate inputs, observe outputs/feedback from systems, and use the feedback to guide the design of subsequent inputs. While many policies are developed under structural assumptions on the underlying systems, many real-world systems operate without such knowledge, necessitating black-box policies that lack a unified evaluation framework. We introduce a stochastic framework that models and evaluates such policies using Markov chains and simulation, t

Mengfan Xu, Zirui Liu, Juan Zhai·5 days ago
23
NLPAINLP

Do Verifier Judgments Survive Abstraction? Measuring Verification Transport for LLM Agent Evaluation

LLM-based verifiers are increasingly used to evaluate agent executions, but their reliability is typically measured under a single representation of the trajectory. In deployed agent systems, the same execution may be exposed through composed tools, delegation boundaries, or compacted histories, changing what execution evidence is directly observable to the verifier. It therefore remains unclear whether correct verifier judgments persist across such abstraction boundaries. We introduce Verification Transport, a reliability test that measures judgment stability under abstraction-induced changes

Disha Sheshanarayana, Sai Linisha Reddy Goli·5 days ago
24
ML

Contrastive latent representation learning with denoising score matching

Contrastive representation learning methods operate by pulling different views of the same data sample together while pushing them away from views of different samples. A fundamental challenge is the estimation of the repulsive force, which typically requires large batch sizes, can exhibit high variance, and is susceptible to the curse of dimensionality. We introduce ScoreCLR, a contrastive representation learning method that offers a novel way to estimate this repulsion term. We consider the framework of representation learning by maximizing the mutual information between two latent views of

Christopher Marouani, Grigory Bartosh, Christian A. Naesseth·5 days ago