papers.joyehuang.me

Paper Recommendations

Daily AI-powered curation from arXiv and Hugging Face Daily Papers. Last updated May 14, 2026 · 23:01 UTC.

Archive joyehuang.me Source
92
Candidates
50
Top Picks
1
Blockbusters
16
Max Score
Today's Picks

Editor's Rationale

**1. MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning** - Core Contribution: Proposes a "map-then-act" paradigm where agents build environmental cognitive maps before execution, solving the "epistemic bottleneck" problem where current stepwise planning agents learn through trial-and-error during execution. - Why Recommend: Directly addresses a core pain point in agent architecture design - agents repeatedly trial-and-error because they lack environmental understanding. MAP's plug-and-play framework can integrate with existing agent systems. On ARC-AGI-3, it enables frontier models to go from near-zero to 22/25 game environment success rate. **2. FlowCompile: An Optimizing Compiler for Structured LLM Workflows** - Core Contribution: Treats structured LLM workflow (multi sub-agent DAG) optimization as a compilation problem rather than a routing problem. Pre-deployment compile-time design space exploration generates reusable configuration sets achieving up to 6.4x speedup. - Why Recommend: If you're building multi-agent orchestration systems, you've faced the combinatorial explosion of "which model, what budget, how to structure." FlowCompile's compiler-inspired approach is novel - a one-time global optimization that produces accuracy-latency Pareto fronts. Great reference for teams building MCP/A2A architectures. **3. MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading** - Core Contribution: Addresses the "memorize-while-reading" evidence loss problem by triggering question decomposition and rereading when final memory is insufficient, supporting non-linear reasoning while maintaining linear time complexity. - Why Recommend: Context management is a key bottleneck for agent deployment. MemReread's "streaming read + reread when needed" strategy is practical, especially for agents processing very long documents. RL-based dynamic control of reread passes avoids the efficiency issues of fixed strategies. **4. HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution** - Core Contribution: Proposes a weighted multi-relational memory framework reconceptualizing retrieval as sequential, query-conditioned graph traversal, using RL to jointly optimize routing behavior and edge representations. - Why Recommend: Traditional agent memory systems use flat vector search or fixed binary relation graphs with limited expressiveness. HAGE's trainable weighted edges + query-conditioned routing is an elegant design that provides practical inspiration for building complex agent memory systems.

Top Picks

50 papers
#01 16

PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents

Mikhail Menschikov, Matvey Iskornev, Alexander Kharitonov et al.
We introduce PersonalAI 2.0 (PAI-2), a novel framework, designed to enhance large language model (LLM) based systems through integration of external knowledge graphs (KG). The proposed approach addresses key limitations of existing Graph Retrieval-Augmented Generation (GraphRAG) …
agentplanningreasoningRAGretrieval-augmentedevaluation
#02 14

Harnessing Agentic Evolution

Jiayi Zhang, Yongfeng Gu, Jianhao Ruan et al.
cs.AI, cs.LG
Agentic evolution has emerged as a powerful paradigm for improving programs, workflows, and scientific solutions by iteratively generating candidates, evaluating them, and using feedback to guide future search. However, existing methods are typically instantiated either as fixed …
agentagenticreasoningworkflowevaluationbenchmark
#03 13

An Empirical Study of Automating Agent Evaluation

Kang Zhou, Sangmin Woo, Haibo Ding et al.
Agent evaluation requires assessing complex multi-step behaviors involving tool use and intermediate reasoning, making it costly and expertise-intensive. A natural question arises: can frontier coding assistants reliably automate this evaluation process? Our study shows that simp…
agenttool usereasoningRAGevaluationbenchmark
#04 13

Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization

Xingyuan Hua, Sheng Yue, Ju Ren
Recent advancements in agentic test-time scaling allow models to gather environmental feedback before committing to final actions. A key limitation of existing methods is that they typically employ undifferentiated exploration strategies, lacking the ability to adaptively disting…
agentagenticreasoningbenchmark
#05 13

MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading

Baibei Ji, Xiaoyang Weng, Juntao Li et al.
To tackle long-context reasoning tasks without the quadratic complexity of standard attention mechanisms, approaches based on agent memory have emerged, which typically maintain a dynamically updated memory when linearly processing document chunks. To mitigate the potential loss …
agentagenticreasoningPPO
#06 13

MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning

Yuxin Liu, Ziang Ye, Yueqing Sun et al.
Current interactive LLM agents rely on goal-conditioned stepwise planning, where environmental understanding is acquired reactively during execution rather than established beforehand. This temporal inversion leads to Delayed Environmental Perception: agents must infer environmen…
agentReActplanningreasoningbenchmark
#07 11

Good Agentic Friends Do Not Just Give Verbal Advice: They Can Update Your Weights

Wenrui Bao, Huan Wang, Jian Wang et al.
cs.CL
Multi-agent LLM systems usually collaborate by exchanging natural-language messages. This interface is simple and interpretable, but it forces each sender's intermediate computation to be serialized into tokens and then reprocessed by the receiver, thereby increasing the generate…
agentmulti-agentagenticbenchmark
#08 11

Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation

Jiashuo Sun, Jimeng Shi, Yixuan Xie et al.
Retrieval-Augmented Generation (RAG) has become a standard approach for knowledge-intensive question answering, but existing systems remain brittle on multi-hop questions, where solving the task requires chaining multiple retrieval and reasoning steps. Key challenges are that cur…
reflectionreasoningRAGretrieval-augmentedbenchmark
#09 11

HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution

Dongming Jiang, Yi Li, Guanpeng Li et al.
Memory retrieval in agentic large language model (LLM) systems is often treated as a static lookup problem, relying on flat vector search or fixed binary relational graphs. However, fixed graph structures cannot capture the varying strength, confidence, and query-dependent releva…
agentagenticreasoningembedding
#10 10

FlowCompile: An Optimizing Compiler for Structured LLM Workflows

Junyan Li, Zhang-Wei Hong, Maohao Shen et al.
cs.CL
Structured LLM workflows, where specialized LLM sub-agents execute according to a predefined graph, have become a powerful abstraction for solving complex tasks. Optimizing such workflows, i.e., selecting configurations for each sub-agent to balance accuracy and latency, is chall…
agentreasoningworkflowbenchmarkPPO
#11 10

RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitation

Chengzhi Shen, Weixiang Shen, Tobias Susetzky et al.
cs.AI, cs.CL, cs.LG, cs.MA
Intensive care units (ICU) generate long, dense and evolving streams of clinical information, where physicians must repeatedly reassess patient states under time pressure, underscoring a clear need for reliable AI decision support. Existing ICU benchmarks typically treat historic…
agentreasoningbenchmarkPPO
#12 10

Source or It Didn't Happen: A Multi-Agent Framework for Citation Hallucination Detection

Mingzhe Li, Zhiqiang Lin, Shiqing Ma
Large language models are increasingly used in scientific writing, yet they can fabricate citation-shaped references that appear plausible but fail bibliographic verification. Existing detectors often reduce verification to binary found/not-found decisions and rely on brittle par…
agentmulti-agentbenchmarkhallucination
#13 10

Many-Shot CoT-ICL: Making In-Context Learning Truly Learn

Tsz Ting Chung, Lemao Liu, Mo Yu et al.
In-context learning (ICL) adapts large language models (LLMs) to new tasks by conditioning on demonstrations in the prompt without parameter updates. With long-context models, many-shot ICL can use dozens to hundreds of examples and achieve performance comparable to fine-tuning, …
reasoningfine-tuningcontext windowlong contextchain-of-thoughtCoT
#14 10

Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context

Zhaowei Wang, Lishu Luo, Haodong Duan et al.
Long-context modeling is becoming a core capability of modern large vision-language models (LVLMs), enabling sustained context management across long-document understanding, video analysis, and multi-turn tool use in agentic workflows. Yet practical training recipes remain insuff…
agentagentictool usereasoningworkflow
#15 9

Qwen-Image-VAE-2.0 Technical Report 🚀

Zekai Zhang, Deqing Li, Kuan Cao et al.
We present Qwen-Image-VAE-2.0, a suite of high-compression Variational Autoencoders (VAEs) that achieve significant advances in both reconstruction fidelity and diffusability. To address the reconstruction bottlenecks of high compression, we adopt an improved architecture featuri…
RAGevaluationbenchmarkalignment
#16 9

Learning Agentic Policy from Action Guidance

Yuxiang Ji, Zengbin Wang, Yong Wang et al.
Agentic reinforcement learning (RL) for Large Language Models (LLMs) critically depends on the exploration capability of the base policy, as training signals emerge only within its in-capability region. For tasks where the base policy cannot reach reward states, additional traini…
agentagenticbenchmark
#17 9

PresentAgent-2: Towards Generalist Multimodal Presentation Agents

Wei Wu, Ziyang Xu, Zeyu Zhang et al.
Presentation generation is moving beyond static slide creation toward end-to-end presentation video generation with research grounding, multimodal media, and interactive delivery. We introduce PresentAgent-2, an agentic framework for generating presentation videos from user queri…
agentagenticevaluationbenchmarkPPO
#18 7

LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models

Songtao Wei, Yi Li, Zhikai Li et al.
Large reasoning models, such as OpenAI o1 and DeepSeek-R1, tend to become increasingly verbose as their reasoning capabilities improve. These inflated Chain-of-Thought (CoT) trajectories often exceed what the underlying problems require, wasting compute, latency, and context budg…
reasoningbenchmarkchain-of-thoughtCoT
#19 7

AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation

Priyam Sahoo, Gaurav Mittal, Xiaomin Li et al.
Evaluation of software engineering (SWE) agents is dominated by a binary signal: whether the final patch passes the tests. This outcome-only view treats a principled solution and a chaotic trial-and-error process as equivalent. We show that this equivalence is empirically false. …
agentorchestrationevaluation
#20 6

EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents

Tara Bogavelli, Gabrielle Gauthier Melançon, Katrina Stankiewicz et al.
cs.SD, cs.AI, cs.CL, cs.LG
Voice agents, artificial intelligence systems that conduct spoken conversations to complete tasks, are increasingly deployed across enterprise applications. However, no existing benchmark jointly addresses two core evaluation challenges: generating realistic simulated conversatio…
agentevaluationbenchmark
#21 6

RTLC -- Research, Teach-to-Learn, Critique: A three-stage prompting paradigm inspired by the Feynman Learning Technique that lifts LLM-as-judge accuracy on JudgeBench with no fine-tuning

Andrea Morandi
cs.CL, cs.AI
LLM-as-a-judge is now the default measurement instrument for open-ended generation, but on the public JudgeBench benchmark even strong instruction-tuned judges barely scrape past random on objective-correctness pairwise items. We introduce RTLC, a three-stage prompting recipe -- …
reasoningfine-tuningbenchmark
#22 6

MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image

Alan Arazi, Eilam Shapira, Shoham Grunblat et al.
Tabular Foundation Models have recently established the state of the art in supervised tabular learning, by leveraging pretraining to learn generalizable representations of numerical and categorical structured data. However, they lack native support for unstructured modalities su…
RAGbenchmarkPPOembedding
#23 6

SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety

Zhe Liu, Zonghao Ying, Wenxin Zhang et al.
With the rapid evolution of foundation models, Large Language Model (LLM) agents have demonstrated increasingly powerful tool-use capabilities. However, this proficiency introduces significant security risks, as malicious actors can manipulate agents into executing tools to gener…
agenttool-use
#24 6

ShapeCodeBench: A Renewable Benchmark for Perception-to-Program Reconstruction of Synthetic Shape Scenes

Shivam Kumar
We introduce ShapeCodeBench, a synthetic benchmark for perception-to-program reconstruction: given a rendered raster image, a model must emit an executable drawing program that a deterministic evaluator re-renders and compares with the target. The v1 DSL has four primitives on a …
reasoningbenchmarkPPO
#25 6

The DAWN of World-Action Interactive Models

Hongbo Lu, Liang Yao, Chenghao He et al.
A plausible scene evolution depends on the maneuver being considered, while a good maneuver depends on how the scene may evolve. Existing World Action Models (WAMs) largely miss this reciprocity, treating world prediction and action generation as either isolated parallel branches…
planningautonomousbenchmarkPPO
#26 5

LMPath: Language-Mediated Priors and Path Generation for Aerial Exploration

Jonathan A. Diller, Fernando Cladera, Camillo J. Taylor et al.
cs.RO, cs.AI
Traditional autonomous UAV search missions rely on geometric coverage patterns that ignore the semantic context of the target, leading to significant time waste in large-scale environments. In this paper we present LMPath, a pipeline for generating language-mediated exploration p…
planningautonomousRAG
#27 5

Where Does Reasoning Break? Step-Level Hallucination Detection via Hidden-State Transport Geometry

Tyler Alvarez, Ali Baheri
cs.CL, cs.AI
Large language models hallucinate during multi-step reasoning, but most existing detectors operate at the trace level: they assign one confidence score to a full output, fail to localize the first error, and often require multiple sampled completions. We frame hallucination inste…
reasoninghallucination
#28 5

An LLM-Based System for Argument Reconstruction

Paulo Pirozelli, Victor Hugo Nascimento Rocha, Fabio G. Cozman et al.
cs.CL
Arguments are a fundamental aspect of human reasoning, in which claims are supported, challenged, and weighed against one another. We present an end-to-end large language model (LLM)-based system for reconstructing arguments from natural language text into abstract argument graph…
reasoningevaluationbenchmarkPPO
#29 5

RoboEvolve: Co-Evolving Planner-Simulator for Robotic Manipulation with Limited Data

Harold Haodong Chen, Sirui Chen, Yingjie Xu et al.
The scalability of robotic manipulation is fundamentally bottlenecked by the scarcity of task-aligned physical interaction data. While vision-language models (VLMs) and video generation models (VGMs) hold promise for autonomous data synthesis, they suffer from semantic-spatial mi…
autonomousRAGhallucinationalignment
#30 4

History Anchors: How Prior Behavior Steers LLM Decisions Toward Unsafe Actions

Alberto G. Rodríguez Salgado
cs.AI, cs.CV
Frontier LLMs are increasingly deployed as agents that pick the next action after a long log of prior tool calls produced by the same or a different model. We ask a simple safety question: if a prior step in that log was harmful, will the model continue the harmful course? We bui…
agentagentic
#31 4

Improving Reproducibility in Evaluation through Multi-Level Annotator Modeling

Deepak Pandita, Flip Korn, Chris Welty et al.
cs.LG, cs.AI
As generative AI models such as large language models (LLMs) become more pervasive, ensuring the safety, robustness, and overall trustworthiness of these systems is paramount. However, AI is currently facing a reproducibility crisis driven by unreliable evaluations and unrepeatab…
RAGevaluation
#32 4

Force-Aware Neural Tangent Kernels for Scalable and Robust Active Learning of MLIPs

Eszter Varga-Umbrich, Zachary Weller-Davies, Paul Duckworth et al.
cs.LG
Active learning for machine-learning interatomic potentials (MLIPs) must address several challenges to be practical: scaling to large candidate pools, leveraging energy-force supervision, and maintaining robustness when candidate pools are biased relative to the target distributi…
RAGfine-tuningbenchmarkembedding
#33 4

Children's English Reading Story Generation via Supervised Fine-Tuning of Compact LLMs with Controllable Difficulty and Safety

Qian Shen, Fanghua Cao, Min Yao et al.
cs.CL, cs.AI, cs.LG
Large Language Models (LLMs) are widely applied in educational practices, such as for generating children's stories. However, the generated stories are often too difficult for children to read, and the operational cost of LLMs hinders their widespread adoption in educational sett…
fine-tuningevaluation
#34 4

Fine-tuning with Hierarchical Prompting for Robust Propaganda Classification Across Annotation Schemas

Lukas Stähelin, Veronika Solopova, Max Upravitelev et al.
cs.CL, cs.CY
Propaganda detection in social media is challenging due to noisy, short texts and low annotation agreements. We introduce a new intent-focused taxonomy of propaganda techniques and compare it against an established, higher-agreement schema. Along three dimensions (model portfolio…
fine-tuningbenchmark
#35 4

Prefix Teach, Suffix Fade: Local Teachability Collapse in Strong-to-Weak On-Policy Distillation

Kaiyuan Liu, Ziyuan Zhuang, Yang Bai et al.
cs.CL
On-policy distillation (OPD) trains a student model on its own rollouts using dense feedback from a stronger teacher. Prior literature suggests that, provided teacher feedback is available, supervising the full sequence of response tokens should monotonically improve performance.…
benchmark
#36 4

Multi-Objective and Mixed-Reward Reinforcement Learning via Reward-Decorrelated Policy Optimization

Yang Bai, Kaiyuan Liu, Ziyuan Zhuang et al.
cs.LG, cs.CL
Complex reinforcement learning environments frequently employ multi-task and mixed-reward formulations. In these settings, heterogeneous reward distributions and correlated reward dimensions often destabilize the construction of scalar advantages. To address these challenges, we …
reasoningevaluationDPO
#37 4

Vividh-ASR: A Complexity-Tiered Benchmark and Optimization Dynamics for Robust Indic Speech Recognition

Kush Juvekar, Kavya Manohar, Aditya Srinivas Menon et al.
Fine-tuning multilingual ASR models like Whisper for low-resource languages often improves read speech but degrades spontaneous audio performance, a phenomenon we term studio-bias. To diagnose this mismatch, we introduce Vividh-ASR, a complexity-stratified benchmark for Hindi and…
fine-tuningbenchmark
#38 4

Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling

Eilam Shapira, Moshe Tennenholtz, Roi Reichart
AI agents negotiate and transact in natural language with unfamiliar counterparts: a buyer bot facing an unknown seller, or a procurement assistant negotiating with a supplier. In such interactions, the counterpart's LLM, prompts, control logic, and rule-based fallbacks are hidde…
agent
#39 3

MinT: Managed Infrastructure for Training and Serving Millions of LLMs

Mind Lab, :, Song Cao et al.
cs.LG, cs.AI, cs.DC
We present MindLab Toolkit (MinT), a managed infrastructure system for Low-Rank Adaptation (LoRA) post-training and online serving. MinT targets a setting where many trained policies are produced over a small number of expensive base-model deployments. Instead of materializing ea…
evaluationPPOGRPO
#40 3

Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs

Trung Nguyen Quang, Yiming Gao, Fanyi Pu et al.
cs.AI, cs.CL
When an omnimodal large language model accepts a question whose textual premise contradicts what it actually sees or hears, does the failure lie in perception or in action? Recent omnimodal models are positioned as perception-grounded agents that jointly process video, audio, and…
agentbenchmark
#41 3

R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow

Zijie Wu, Lixin Xu, Puhua Jiang et al.
cs.CV, cs.GR, cs.LG
Video-guided 3D animation holds immense potential for content creation, offering intuitive and precise control over dynamic assets. However, practical deployment faces a critical yet frequently overlooked hurdle: the pose misalignment dilemma. In real-world scenarios, the initial…
RAGPPOalignment
#42 3

QLAM: A Quantum Long-Attention Memory Approach to Long-Sequence Token Modeling

Hoang-Quan Nguyen, Sankalp Pandey, Khoa Luu
cs.LG, cs.CV
Modeling long-range dependencies in sequential data remains a central challenge in machine learning. Transformers address this challenge through attention mechanisms, but their quadratic complexity with respect to sequence length limits scalability to long contexts. State-space m…
RAGbenchmarklong context
#43 3

Uncertainty-Driven Anomaly Detection for Psychotic Relapse Using Smartwatches: Forecasting and Multi-Task Learning Fusion

Nikolaos Tsalkitzis, Panagiotis P. Filntisis, Petros Maragos et al.
cs.LG
Digital phenotyping enables continuous passive monitoring of behavior and physiology, offering a promising paradigm for early detection of psychotic relapse. In this work, we develop and systematically study two smartwatch-based frameworks for daily relapse detection. The first f…
benchmarkPPOembedding
#44 3

Creativity Bias: How Machine Evaluation Struggles with Creativity in Literary Translations

Kyo Gerrits, Rik van Noord, Ana Guerberof Arenas
cs.CL
This article investigates the performance of automatic evaluation metrics (AEMs) and LLM-as-a-judge evaluation on literary translation across multiple languages, genres, and translation modalities. The aim is to assess how well these tools align with professionals when evaluating…
evaluation
#45 3

Retrieval from Within: An Intrinsic Capability of Attention-Based Models

Elad Hoffer, Yochai Blau, Edan Kinderman et al.
Retrieval-augmented generation (RAG) typically treats retrieval and generation as separate systems. We ask whether an attention-based encoder-decoder can instead retrieve directly from its own internal representations. We introduce INTRA (INTrinsic Retrieval via Attention), a fra…
RAGretrieval-augmentedbenchmark
#46 3

FrameSkip: Learning from Fewer but More Informative Frames in VLA Training

Bin Yu, Shijie Lian, Xiaopeng Lin et al.
Vision-Language-Action (VLA) policies are commonly trained from dense robot demonstration trajectories, often collected through teleoperation, by sampling every recorded frame as if it provided equally useful supervision. We argue that this convention creates a temporal supervisi…
RAGbenchmarkalignment
#47 3

Offline Preference Optimization for Rectified Flow with Noise-Tracked Pairs

Yunhong Lu, Qichao Wang, Hengyuan Cao et al.
Existing preference datasets for text-to-image models typically store only the final winner/loser images. This representation is insufficient for rectified flow (RF) models, whose generation is naturally indexed by a specific prior noise sample and follows a nearly straight denoi…
RAGDPOalignment
#48 3

F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking

Rohan Surana, Gagan Mundada, Junda Wu et al.
Traditional retrieval pipelines optimize utility through stages of candidate retrieval and reranking, where ranking operates over a predefined candidate set. Large Language Models (LLMs) broaden this into a generative process: given a candidate pool, an LLM can generate a subset …
RAGbenchmarkGRPO
#49 3

TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking

Jisu Nam, Jahyeok Koo, Soowon Son et al.
Dense 3D tracking from monocular video is fundamental to dynamic scene understanding. While recent 3D foundation models provide reliable per-frame geometry, recovering object motion in this geometry remains challenging and benefits from strong motion priors learned from real-worl…
fine-tuningbenchmarkalignment
#50 3

Visual Aesthetic Benchmark: Can Frontier Models Judge Beauty?

Yichen Feng, Yuetai Li, Chunjiang Liu et al.
Multimodal large language models (MLLMs) are now routinely deployed for visual understanding, generation, and curation. A substantial fraction of these applications require an explicit aesthetic judgment. Most existing solutions reduce this judgment to predicting a scalar score f…
fine-tuningevaluationbenchmark

All Candidates

92 papers
ScorePaperAuthorsCategory
3 Position: LLM Inference Should Be Evaluated as Energy-to-Token Production Xiang Liu, Shimiao Yuan et al.
2 Neurosymbolic Auditing of Natural-Language Software Requirements Bethel Hall, William Eiers cs.SE, cs.AI
2 (How) Do Large Language Models Understand High-Level Message Sequence Charts? Mohammad Reza Mousavi cs.SE, cs.AI, cs.LO
2 Reducing cross-sample prediction churn in scientific machine learning Gordan Prastalo, Kevin Maik Jablonka cs.LG, cond-mat.mtrl-sci, physics.chem-ph
2 Parallel Scan Recurrent Neural Quantum States for Scalable Variational Monte Carlo Ejaaz Merali, Mohamed Hibat-Allah et al. cond-mat.str-el, cond-mat.dis-nn, cs.LG, physics.c
2 Edit-level Majority Voting Mitigates Over-Correction in LLM-based Grammatical Error Correction Takumi Goto, Yusuke Sakai et al. cs.CL
2 MC-RFM: Geometry-Aware Few-Shot Adaptation via Mixed-Curvature Riemannian Flow Matching Salim Khazem, Ibrahim Mohamed Serouis et al.
2 BEACON: A Multimodal Dataset for Learning Behavioral Fingerprints from Gameplay Data Ishpuneet Singh, Gursmeep Kaur et al.
2 M2Retinexformer: Multi-Modal Retinexformer for Low-Light Image Enhancement Youssef Aboelwafa, Hicham G. Elmongui et al.
2 From Pixels to Concepts: Do Segmentation Models Understand What They Segment? Shuang Liang, Zeqing Wang et al.
2 Context Training with Active Information Seeking Zeyu Huang, Adhiguna Kuncoro et al.
1 WARDEN: Endangered Indigenous Language Transcription and Translation with 6 Hours of Training Data Ziheng Zhang, Yunzhong Hou et al. cs.CL, cs.AI
1 Quantifying Sensitivity for Tree Ensembles: A symbolic and compositional approach S. Akshay, Chaitanya Garg et al. cs.AI, cs.LG
1 Negation Neglect: When models fail to learn negations in training Harry Mayne, Lev McKinney et al. cs.CL, cs.AI, cs.LG
1 Di-BiLPS: Denoising induced Bidirectional Latent-PDE-Solver under Sparse Observations Zhonghao Li, Chaoyu Liu et al. cs.LG, cs.AI
1 KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving Zedong Liu, Xinyang Ma et al. cs.DC, cs.AI, cs.NI
1 Interpretable Machine Learning for Antepartum Prediction of Pregnancy-Associated Thrombotic Microangiopathy Using Routine Longitudinal Laboratory Data Chuanchuan Sun, Zhen Yu et al. cs.LG
1 Attention Once Is All You Need: Efficient Streaming Inference with Stateful Transformers Victor Norgren cs.LG
1 Dense vs Sparse Pretraining at Tiny Scale: Active-Parameter vs Total-Parameter Matching Abdalrahman Wael cs.CL, cs.LG
1 Federation of Experts: Communication Efficient Distributed Inference for Large Language Models Muhammad Shahir Abdurrahman, Chun Deng et al.
1 Active Tabular Augmentation via Policy-Guided Diffusion Inpainting Zheyu Zhang, Shuo Yang et al.
1 IndicMedDialog: A Parallel Multi-Turn Medical Dialogue Dataset for Accessible Healthcare in Indic Languages Shubham Kumar Nigam, Suparnojit Sarkar et al.
1 FAAST: Forward-Only Associative Learning via Closed-Form Fast Weights for Test-Time Supervised Adaptation Guangsheng Bao, Hongbo Zhang et al.
1 FeatCal: Feature Calibration for Post-Merging Models Yanggan Gu, Shuo Cai et al.
1 AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation Yuchao Gu, Guian Fang et al.
1 Revisiting DAgger in the Era of LLM-Agents Changhao Li, Rushi Qiang et al.
0 Topology-Preserving Neural Operator Learning via Hodge Decomposition Dongzhe Zheng, Tao Zhong et al. cs.LG, cs.AI, cs.CG
0 ENSEMBITS: an alphabet of protein conformational ensembles Kaiwen Shi, Carlos Oliver cs.LG, cs.AI, q-bio.BM
0 Amplification to Synthesis: A Comparative Analysis of Cognitive Operations Before and After Generative AI Liz Cho, Dongwook Yoon cs.CY, cs.AI
0 High-Rate Quantized Matrix Multiplication II Or Ordentlich, Yury Polyanskiy cs.LG, cs.AI, cs.IT
0 Weakly-Supervised Spatiotemporal Anomaly Detection Urvi Gianchandani, Praveen Tirupattur et al. cs.CV, cs.AI
0 What is Learnable in Valiant's Theory of the Learnable? Steve Hanneke, Anay Mehrotra et al. stat.ML, cs.DS, cs.LG, math.ST, stat.CO
0 Provable Quantization with Randomized Hadamard Transform Ying Feng, Piotr Indyk et al. cs.LG, cs.DS
0 Min-Max Optimization Requires Exponentially Many Queries Martino Bernasconi, Matteo Castiglioni et al. cs.DS, cs.CC, cs.GT, cs.LG, math.OC
0 Beyond Perplexity: A Geometric and Spectral Study of Low-Rank Pre-Training Namrata Shivagunde, Vijeta Deshpande et al. cs.LG, cs.AI, cs.CL
0 Inducing Artificial Uncertainty in Language Models Sophia Hager, Simon Zeng et al. cs.CL
0 Locale-Conditioned Few-Shot Prompting Mitigates Demonstration Regurgitation in On-Device PII Substitution with Small Language Models Anuj Sadani, Deepak Kumar cs.CL, cs.AI
0 From Generalist to Specialist Representation Yujia Zheng, Fan Feng et al.
0 Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion Chien Van Nguyen, Chaitra Hegde et al.
0 Asymmetric Flow Models Hansheng Chen, Jan Ackermann et al.
0 WriteSAE: Sparse Autoencoders for Recurrent State Jack Young
0 The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputs Xin Li, Hao Jiang et al.