Developer Tools B

This paper presents a robust Q-learning algorithm for discrete-time mean-field control problems with common noise, accounting for Wasserstein uncertainty in the model.

The paper proposes a quantum ring all-reduce scheme for distributed learning, arguing that quantum communication can make distributed training both more communication-efficient and information-theoretically private. The approach is discussed for both classical and quantum settings.

Agent skills are commonly deployed as natural-language Markdown files that encode answer policies. SoftSkill compresses such behaviors to enable more efficient contextual adaptation.

The paper develops QCPIKAN, a quantum-classical physics-informed Kolmogorov-Arnold network for solving partial differential equations. The hybrid framework combines Chebyshev-polynomial KAN layers with parameterized quantum circuits and embeds physical constraints into the training loss.

Deep transfer learning enables efficient construction of intelligent fault diagnosis systems. This work leverages systems' non-linearity to tackle the scarcity of data in their design.

The paper proposes a token-operations-oriented framework for large-model inference optimization, presenting a four-layer technical architecture aimed at scalable, low-cost, and stable large-model services. The layers include components such as multi-model fusion.

The paper proposes a shifting-based method for constructing optimizable linear relaxations of general activation functions, used in formal verification of neural networks. It removes the need for hand-crafted relaxations tailored to each activation, supporting formal guarantees in safety- and security-critical settings.

The paper integrates national forest inventory data, airborne lidar, and satellite imagery with computer vision to produce wall-to-wall maps of forest structure. It targets the persistent need for annually updated, large-landscape maps to support forest and wildfire risk management.

The paper presents PsyScore, a psychometrically-aware framework for automated essay scoring that adapts to writing traits and provides ZPD-scaffolded feedback. It aims to unify scoring and feedback, which existing methods treat separately, balancing reliable assessment with interpretable, actionable instruction.

Graph neural networks aggregate neighbor information for classification but entangle structure. This work proposes boundary embedding shaping with adaptive contrastive learning for graph structural disentanglement.

Student-generated drawings are widely used in science education to assess conceptual understanding. This work introduces confidence-aware automated assessment of student-drawn scientific models.

LLM-driven information services are reshaping how public knowledge is produced. This work proposes a participatory approach to engage editorial expertise in LLM-mediated knowledge dissemination.

This work introduces the Meaning Intelligence Framework, a nine-dimension annotation and evaluation scheme, to study the register gap in Nigerian public discourse.

Vision-language models often underperform on evidence-intensive tasks by missing decisive visual cues. SPOT-E applies test-time entropy shaping with visual spotlights to improve frozen VLMs.

Many decision-making problems in computing and networking can be cast as constrained optimization. This work presents a multi-agent system for multi-objective constrained optimization.

Academic paper search is a core step in research, and LLM-based search agents are emerging. ScholarQuest provides a taxonomy-guided benchmark for agentic academic paper search in open literature environments.

Can intelligence be measured? This work proposes defining intelligence as the lawful amplification of order and develops a thermodynamic measure to quantify it.

The paper investigates whether emergent misalignment—induced by fine-tuning language models on insecure code—corresponds to a causally actionable, shared direction in activation space. Across four instruction-tuned model families, it studies using such directions to detect and mitigate the misalignment.

The paper presents CzechDocs, a multiway parallel dataset of formatted documents in HTML, DOCX, and PDF covering Czech and minority languages used in Czechia—primarily Ukrainian and English, with smaller amounts of Vietnamese, Russian, and others. It is designed to support evaluation of machine translation.

Immersion in video games depends not only on graphics, audio, and mechanics but also on the quality of game AI. This work augments game AI using deep reinforcement learning.

The paper studies off-policy evaluation in finite-horizon MDPs when rewards are missing not at random, as in offline reinforcement learning with sparse, irregular, or censored reward records. It develops missingness-aware policies for settings such as health care and marketing.

Psychological instruments designed for humans are increasingly applied to large language models. This work argues that the apparent psychological profiles of LLMs are largely a measurement artifact.

The paper presents an algorithm for pitch spelling and key estimation across jazz lead sheets, solo transcriptions, classical piano, and monophonic scores. Given MIDI-like input with note pitches and bar boundaries, it estimates note names, a global key signature, and local scales.

Neuromorphic computing mimics the brain and can use far less energy than conventional AI chips, yet today devices remain simple. This piece reports research using sound (acoustic) waves to push neuromorphic chips toward more brain-like information processing.

The paper introduces MedRLM, a recursive multimodal health-intelligence system for long-context clinical reasoning, sensor-guided screening, evidence-grounded decision support, and community-to-tertiary referral optimization. It targets reasoning over heterogeneous, longitudinal patient data, beyond the single-step prompting or retrieval of current medical LLMs.

The paper traces how representations of essay quality emerge inside large language models used for automated essay scoring. It systematically analyzes the hidden representations of eight LLMs across two English essay datasets to better understand the internal mechanisms behind LLM-based scoring.

The paper tests whether large language models resist valid corrections to their own writing during verifiable instruction-following revision. Across four models under genuine authorship, it finds that the documented self-preference bias is weak or absent in this revision setting.

A look at CS 6120, an advanced compilers course released as a self-guided online resource. With lectures and assignments, the free course lets learners study advanced topics such as optimization and program analysis on their own.

The paper gives an information-theoretic analysis of what makes supervision effective in latent chain-of-thought reasoning, which internalizes reasoning in continuous hidden states. It examines why outcome supervision provides weak learning signals, making robust latent reasoning difficult.

The paper studies generative engine optimization at scale, measuring how brands are represented, cited, and recommended across AI search engines such as ChatGPT, Claude, Perplexity, and Gemini. It frames the shift from traditional SEO as users increasingly get answers directly from these engines.