The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models
Paper • 2507.23313 • Published • 1
Papers Pertinent or Protuberant
-
-
SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering
Paper • 2508.03448 • Published • 6 -
C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisor
Paper • 2508.01311 • Published • 2 -
Normalized Attention Guidance: Universal Negative Guidance for Diffusion Model
Paper • 2505.21179 • Published • 13 -
Learning to Detect Multi-class Anomalies with Just One Normal Image Prompt
Paper • 2505.09264 • Published • 5 -
How to Reduce Change Detection to Semantic Segmentation
Paper • 2206.07557 • Published -
Real-IAD D3: A Real-World 2D/Pseudo-3D/3D Dataset for Industrial Anomaly Detection
Paper • 2504.14221 • Published -
AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detection
Paper • 2505.09926 • Published • 6 -
MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learning
Paper • 2505.09265 • Published • 5 -
IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards
Paper • 2508.04632 • Published • 2 -
Reasoning Language Models for Root Cause Analysis in 5G Wireless Networks
Paper • 2507.21974 • Published • 5 -
A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding
Paper • 2508.01197 • Published • 5 -
Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management
Paper • 2508.04664 • Published • 13 -
IAUNet: Instance-Aware U-Net
Paper • 2508.01928 • Published • 9 -
Position: The Current AI Conference Model is Unsustainable! Diagnosing the Crisis of Centralized AI Conference
Paper • 2508.04586 • Published • 12 -
LeanK: Learnable K Cache Channel Pruning for Efficient Decoding
Paper • 2508.02215 • Published • 12 -
Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis
Paper • 2507.23785 • Published • 18 -
LaTCoder: Converting Webpage Design to Code with Layout-as-Thought
Paper • 2508.03560 • Published • 24 -
Web-CogReasoner: Towards Knowledge-Induced Cognitive Reasoning for Web Agents
Paper • 2508.01858 • Published • 20 -
Agent Lightning: Train ANY AI Agents with Reinforcement Learning
Paper • 2508.03680 • Published • 140 -
Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens
Paper • 2508.01191 • Published • 240 -
Attention Basin: Why Contextual Position Matters in Large Language Models
Paper • 2508.05128 • Published • 4 -
Unlocking the Potential of MLLMs in Referring Expression Segmentation via a Light-weight Mask Decode
Paper • 2508.04107 • Published • 4 -
Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis
Paper • 2508.04699 • Published • 2 -
RPCANet++: Deep Interpretable Robust PCA for Sparse Object Segmentation
Paper • 2508.04190 • Published • 1 -
I Think, Therefore I Am Under-Qualified? A Benchmark for Evaluating Linguistic Shibboleth Detection in LLM Hiring Evaluations
Paper • 2508.04939 • Published • 2 -
REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation
Paper • 2508.04946 • Published • 1 -
I2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity Linking
Paper • 2508.02243 • Published • 2 -
Learning to Reason for Factuality
Paper • 2508.05618 • Published • 7 -
Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression
Paper • 2508.04979 • Published • 5 -
StrandDesigner: Towards Practical Strand Generation with Sketch Guidance
Paper • 2508.01650 • Published • 6 -
MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes
Paper • 2508.05630 • Published • 9 -
Can Large Multimodal Models Actively Recognize Faulty Inputs? A Systematic Evaluation Framework of Their Input Scrutiny Ability
Paper • 2508.04017 • Published • 11 -
Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?
Paper • 2508.03644 • Published • 25 -
A Practical Guide to Fine-tuning Language Models with Limited Data
Paper • 2411.09539 • Published -
LinguaLIFT: An Effective Two-stage Instruction Tuning Framework for Low-Resource Language Tasks
Paper • 2412.12499 • Published • 2 -
Development of Pre-Trained Transformer-based Models for the Nepali Language
Paper • 2411.15734 • Published -
Extending LLMs to New Languages: A Case Study of Llama and Persian Adaptation
Paper • 2412.13375 • Published -
Facilitating large language model Russian adaptation with Learned Embedding Propagation
Paper • 2412.21140 • Published • 18 -
BayLing 2: A Multilingual Large Language Model with Efficient Language Alignment
Paper • 2411.16300 • Published -
Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers
Paper • 2601.22139 • Published • 1 -
Mirroring the Mind: Distilling Human-Like Metacognitive Strategies into Large Language Models
Paper • 2602.22508 • Published -
Contextual Drag: How Errors in the Context Affect LLM Reasoning
Paper • 2602.04288 • Published -
Knowledge Integration Decay in Search-Augmented Reasoning of Large Language Models
Paper • 2602.09517 • Published • 1 -
Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
Paper • 2603.12180 • Published • 65 -
IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse
Paper • 2603.12201 • Published • 53 -
CREATE: Testing LLMs for Associative Creativity
Paper • 2603.09970 • Published • 15 -
Language of Thought Shapes Output Diversity in Large Language Models
Paper • 2601.11227 • Published • 9 -
What Makes a Good Query? Measuring the Impact of Human-Confusing Linguistic Features on LLM Performance
Paper • 2602.20300 • Published • 4 -
No One Size Fits All: QueryBandits for Hallucination Mitigation
Paper • 2602.20332 • Published • 3 -
REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents
Paper • 2602.14234 • Published • 27 -
Cognitive Models and AI Algorithms Provide Templates for Designing Language Agents
Paper • 2602.22523 • Published • 1 -
Agentic Artificial Intelligence (AI): Architectures, Taxonomies, and Evaluation of Large Language Model Agents
Paper • 2601.12560 • Published -
Shared Nature, Unique Nurture: PRISM for Pluralistic Reasoning via In-context Structure Modeling
Paper • 2602.21317 • Published • 4 -
DIVERGE: Diversity-Enhanced RAG for Open-Ended Information Seeking
Paper • 2602.00238 • Published -
dLLM: Simple Diffusion Language Modeling
Paper • 2602.22661 • Published • 152 -
CD4LM: Consistency Distillation and aDaptive Decoding for Diffusion Language Models
Paper • 2601.02236 • Published -
Autoregressive Models Rival Diffusion Models at ANY-ORDER Generation
Paper • 2601.13228 • Published -
Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding?
Paper • 2602.23225 • Published -
Reasoning Core: A Scalable Procedural Data Generation Suite for Symbolic Pre-training and Post-Training
Paper • 2603.02208 • Published • 4 -
Knowledge Graphs are Implicit Reward Models: Path-Derived Signals Enable Compositional Reasoning
Paper • 2601.15160 • Published • 1 -
Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification
Paper • 2601.22642 • Published • 9 -
Structured Reasoning for Large Language Models
Paper • 2601.07180 • Published • 1 -
Milestones over Outcome: Unlocking Geometric Reasoning with Sub-Goal Verifiable Reward
Paper • 2601.05073 • Published -
P2S: Probabilistic Process Supervision for General-Domain Reasoning Question Answering
Paper • 2601.20649 • Published -
VERGE: Formal Refinement and Guidance Engine for Verifiable LLM Reasoning
Paper • 2601.20055 • Published • 7 -
LLM-Guided Quantified SMT Solving over Uninterpreted Functions
Paper • 2601.04675 • Published -
Decompose-and-Formalise: Recursively Verifiable Natural Language Inference
Paper • 2601.19605 • Published -
Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill Synthesis
Paper • 2602.03279 • Published -
LaSER: Internalizing Explicit Reasoning into Latent Space for Dense Retrieval
Paper • 2603.01425 • Published • 7 -
Latent Chain-of-Thought as Planning: Decoupling Reasoning from Verbalization
Paper • 2601.21358 • Published • 7 -
Latent Thoughts Tuning: Bridging Context and Reasoning with Fused Information in Latent Tokens
Paper • 2602.10229 • Published • 5 -
Beyond Dense States: Elevating Sparse Transcoders to Active Operators for Latent Reasoning
Paper • 2602.01695 • Published -
OpenAutoNLU: Open Source AutoML Library for NLU
Paper • 2603.01824 • Published • 50 -
OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens
Paper • 2603.02138 • Published • 151 -
Transformers converge to invariant algorithmic cores
Paper • 2602.22600 • Published • 3 -
Spilled Energy in Large Language Models
Paper • 2602.18671 • Published • 12 -
Humans and LLMs Diverge on Probabilistic Inferences
Paper • 2602.23546 • Published • 13 -
PRISM: Pushing the Frontier of Deep Think via Process Reward Model-Guided Inference
Paper • 2603.02479 • Published • 20 -
MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning
Paper • 2603.03379 • Published • 32 -
Distribution-Conditioned Transport
Paper • 2603.04736 • Published • 3 -
SageBwd: A Trainable Low-bit Attention
Paper • 2603.02170 • Published • 19 -
Large Multimodal Models as General In-Context Classifiers
Paper • 2602.23229 • Published • 26 -
nabla-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space
Paper • 2603.04948 • Published • 2 -
Mario: Multimodal Graph Reasoning with Large Language Models
Paper • 2603.05181 • Published • 9 -
Reasoning Models Struggle to Control their Chains of Thought
Paper • 2603.05706 • Published • 37 -
Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model
Paper • 2603.05438 • Published • 40 -
ByteFlow: Language Modeling through Adaptive Byte Compression without a Tokenizer
Paper • 2603.03583 • Published • 2 -
Distilling Token-Trained Models into Byte-Level Models
Paper • 2602.01007 • Published -
Proxy Compression for Language Modeling
Paper • 2602.04289 • Published • 3 -
Unlocking Data Value in Finance: A Study on Distillation and Difficulty-Aware Training
Paper • 2603.07223 • Published • 13 -
Believe Your Model: Distribution-Guided Confidence Calibration
Paper • 2603.03872 • Published • 40 -
Beyond Test-Time Training: Learning to Reason via Hardware-Efficient Optimal Control
Paper • 2603.09221 • Published -
ReasonCACHE: Teaching LLMs To Reason Without Weight Updates
Paper • 2602.02366 • Published • 1 -
Causal Concept Graphs in LLM Latent Space for Stepwise Reasoning
Paper • 2603.10377 • Published • 3 -
Lost in Backpropagation: The LM Head is a Gradient Bottleneck
Paper • 2603.10145 • Published • 13 -
MSign: An Optimizer Preventing Training Instability in Large Language Models via Stable Rank Restoration
Paper • 2602.01734 • Published • 32 -
SimpleGPT: Improving GPT via A Simple Normalization Strategy
Paper • 2602.01212 • Published • 3 -
Prism-Δ: Differential Subspace Steering for Prompt Highlighting in Large Language Models
Paper • 2603.10705 • Published • 11 -
Spectral Attention Steering for Prompt Highlighting
Paper • 2603.01281 • Published • 7 -
YaPO: Learnable Sparse Activation Steering Vectors for Domain Adaptation
Paper • 2601.08441 • Published • 8 -
ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning
Paper • 2603.10160 • Published • 26 -
LLM2Vec-Gen: Generative Embeddings from Large Language Models
Paper • 2603.10913 • Published • 44 -
OpenClaw-RL: Train Any Agent Simply by Talking
Paper • 2603.10165 • Published • 151 -
How to Mitigate Information Loss in Knowledge Graphs for GraphRAG: Leveraging Triple Context Restoration and Query-Driven Feedback
Paper • 2501.15378 • Published -
Millions of GeAR-s: Extending GraphRAG to Millions of Documents
Paper • 2507.17399 • Published -
RAG vs. GraphRAG: A Systematic Evaluation and Key Insights
Paper • 2502.11371 • Published -
PROPEX-RAG: Enhanced GraphRAG using Prompt-Driven Prompt Execution
Paper • 2511.01802 • Published • 2 -
HELP: HyperNode Expansion and Logical Path-Guided Evidence Localization for Accurate and Efficient GraphRAG
Paper • 2602.20926 • Published • 3 -
PolyG: Effective and Efficient GraphRAG with Adaptive Graph Traversal
Paper • 2504.02112 • Published • 2 -
GraphRAG-R1: Graph Retrieval-Augmented Generation with Process-Constrained Reinforcement Learning
Paper • 2507.23581 • Published -
Deep GraphRAG: A Balanced Approach to Hierarchical Retrieval and Adaptive Integration
Paper • 2601.11144 • Published • 3 -
Enhancing Startup Success Predictions in Venture Capital: A GraphRAG Augmented Multivariate Time Series Method
Paper • 2408.09420 • Published -
NerVE: Nonlinear Eigenspectrum Dynamics in LLM Feed-Forward Networks
Paper • 2603.06922 • Published • 2 -
Divergent-Convergent Thinking in Large Language Models for Creative Problem Generation
Paper • 2512.23601 • Published -
DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use
Paper • 2603.11076 • Published • 5 -
Training Language Models via Neural Cellular Automata
Paper • 2603.10055 • Published • 8 -
Tiny Aya: Bridging Scale and Multilingual Depth
Paper • 2603.11510 • Published • 7 -
Attention Sinks Are Provably Necessary in Softmax Transformers: Evidence from Trigger-Conditional Tasks
Paper • 2603.11487 • Published • 2 -
WildGraphBench: Benchmarking GraphRAG with Wild-Source Corpora
Paper • 2602.02053 • Published • 41 -
Fine-Grained Activation Steering: Steering Less, Achieving More
Paper • 2602.04428 • Published -
A Practical Approach for Building Production-Grade Conversational Agents with Workflow Graphs
Paper • 2505.23006 • Published • 1 -
XSkill: Continual Learning from Experience and Skills in Multimodal Agents
Paper • 2603.12056 • Published • 33 -
mHC: Manifold-Constrained Hyper-Connections
Paper • 2512.24880 • Published • 322 -
Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process
Paper • 2512.23988 • Published • 19 -
Routing the Lottery: Adaptive Subnetworks for Heterogeneous Data
Paper • 2601.22141 • Published • 3 -
Linear representations in language models can change dramatically over a conversation
Paper • 2601.20834 • Published • 21 -
The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain
Paper • 2509.26507 • Published • 550 -
AutoRefine: From Trajectories to Reusable Expertise for Continual LLM Agent Refinement
Paper • 2601.22758 • Published • 1 -
Spectral Surgery: Training-Free Refinement of LoRA via Gradient-Guided Singular Value Reweighting
Paper • 2603.03995 • Published -
Poem Meter Classification of Recited Arabic Poetry: Integrating High-Resource Systems for a Low-Resource Task
Paper • 2504.12172 • Published -
Alignment Makes Language Models Normative, Not Descriptive
Paper • 2603.17218 • Published • 46