Paperium - Forem

Cover image for PEAR: Phase Entropy Aware Reward for Efficient Reasoning

Paperium

Nov 1

PEAR: Phase Entropy Aware Reward for Efficient Reasoning

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for ReLook: Vision-Grounded RL with a Multimodal LLM Critic for Agentic Web Coding

Paperium

Nov 1

ReLook: Vision-Grounded RL with a Multimodal LLM Critic for Agentic Web Coding

#ai #deeplearning #computerscience #machinelearning

2 min read

Cover image for Skill-Targeted Adaptive Training

Paperium

Nov 1

Skill-Targeted Adaptive Training

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for High-Fidelity Simulated Data Generation for Real-World Zero-Shot RoboticManipulation Learning with Gaussian Splatting

Paperium

Oct 31

High-Fidelity Simulated Data Generation for Real-World Zero-Shot RoboticManipulation Learning with Gaussian Splatting

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in LargeVision-Language Models

Paperium

Oct 31

On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in LargeVision-Language Models

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images

Paperium

Oct 31

CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models

Paperium

Oct 31

SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning

Paperium

Oct 31

Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for AdaViewPlanner: Adapting Video Diffusion Models for Viewpoint Planning in 4DScenes

Paperium

Oct 31

AdaViewPlanner: Adapting Video Diffusion Models for Viewpoint Planning in 4DScenes

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for GIR-Bench: Versatile Benchmark for Generating Images with Reasoning

Paperium

Oct 31

GIR-Bench: Versatile Benchmark for Generating Images with Reasoning

#ai #deeplearning #computerscience #machinelearning

2 min read

Cover image for Don't Just Fine-tune the Agent, Tune the Environment

Paperium

Oct 31

Don't Just Fine-tune the Agent, Tune the Environment

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for DocReward: A Document Reward Model for Structuring and Stylizing

Paperium

Oct 31

DocReward: A Document Reward Model for Structuring and Stylizing

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark forEvaluating LLMs

Paperium

Oct 31

FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark forEvaluating LLMs

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions

Paperium

Oct 31

BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for ACADREASON: Exploring the Limits of Reasoning Models with Academic ResearchProblems

Paperium

Oct 31

ACADREASON: Exploring the Limits of Reasoning Models with Academic ResearchProblems

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for Building a Foundational Guardrail for General Agentic Systems via Synthetic Data

Paperium

Oct 31

Building a Foundational Guardrail for General Agentic Systems via Synthetic Data

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models

Paperium

Oct 31

InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for Demystifying Reinforcement Learning in Agentic Reasoning

Paperium

Oct 31

Demystifying Reinforcement Learning in Agentic Reasoning

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for Making Mathematical Reasoning Adaptive

Paperium

Oct 31

Making Mathematical Reasoning Adaptive

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training

Paperium

Oct 31

DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration

Paperium

Oct 31

AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for Spotlight on Token Perception for Multimodal Reinforcement Learning

Paperium

Oct 31

Spotlight on Token Perception for Multimodal Reinforcement Learning

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for RLFR: Extending Reinforcement Learning for LLMs with Flow Environment

Paperium

Oct 31

RLFR: Extending Reinforcement Learning for LLMs with Flow Environment

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for Latent Refinement Decoding: Enhancing Diffusion-Based Language Models byRefining Belief States

Paperium

Oct 31

Latent Refinement Decoding: Enhancing Diffusion-Based Language Models byRefining Belief States

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs

Paperium

Oct 30

OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs

#ai #deeplearning #computerscience #machinelearning

2 min read

Cover image for Diffusion Transformers with Representation Autoencoders

Paperium

Oct 30

Diffusion Transformers with Representation Autoencoders

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs

Paperium

Oct 30

QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for Instant4D: 4D Gaussian Splatting in Minutes

Paperium

Oct 30

Instant4D: 4D Gaussian Splatting in Minutes

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL

Paperium

Oct 30

ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL

#ai #deeplearning #computerscience #machinelearning

2 min read

Cover image for Temporal Prompting Matters: Rethinking Referring Video Object Segmentation

Paperium

Oct 30

Temporal Prompting Matters: Rethinking Referring Video Object Segmentation

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for LLM4Cell: A Survey of Large Language and Agentic Models for Single-Cell Biology

Paperium

Oct 30

LLM4Cell: A Survey of Large Language and Agentic Models for Single-Cell Biology

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for Formalizing Style in Personal Narratives

Paperium

Oct 30

Formalizing Style in Personal Narratives

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall

Paperium

Oct 30

ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?

Paperium

Oct 30

LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for Better Together: Leveraging Unpaired Multimodal Data for Stronger UnimodalModels

Paperium

Oct 30

Better Together: Leveraging Unpaired Multimodal Data for Stronger UnimodalModels

#ai #deeplearning #computerscience #machinelearning

2 min read

Cover image for Speculative Jacobi-Denoising Decoding for Accelerating AutoregressiveText-to-image Generation

Paperium

Oct 30

Speculative Jacobi-Denoising Decoding for Accelerating AutoregressiveText-to-image Generation

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance forSelf-supervised Monocular Depth Estimation

Paperium

Oct 30

Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance forSelf-supervised Monocular Depth Estimation

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework

Paperium

Oct 30

One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework

#ai #deeplearning #computerscience #machinelearning

2 min read

Cover image for Understanding DeepResearch via Reports

Paperium

Oct 29

Understanding DeepResearch via Reports

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for GTAlign: Game-Theoretic Alignment of LLM Assistants for Mutual Welfare

Paperium

Oct 29

GTAlign: Game-Theoretic Alignment of LLM Assistants for Mutual Welfare

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols

Paperium

Oct 29

Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for Mitigating Overthinking through Reasoning Shaping

Paperium

Oct 29

Mitigating Overthinking through Reasoning Shaping

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for TC-LoRA: Temporally Modulated Conditional LoRA for Adaptive Diffusion Control

Paperium

Oct 29

TC-LoRA: Temporally Modulated Conditional LoRA for Adaptive Diffusion Control

#ai #deeplearning #computerscience #machinelearning

3

1 min read

Cover image for A Goal Without a Plan Is Just a Wish: Efficient and Effective Global PlannerTraining for Long-Horizon Agent Tasks

Paperium

Oct 29

A Goal Without a Plan Is Just a Wish: Efficient and Effective Global PlannerTraining for Long-Horizon Agent Tasks

#ai #deeplearning #computerscience #machinelearning

2 min read

Cover image for Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in SpokenLanguage Models

Paperium

Oct 29

Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in SpokenLanguage Models

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for Parallel Test-Time Scaling for Latent Reasoning Models

Paperium

Oct 29

Parallel Test-Time Scaling for Latent Reasoning Models

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for Pseudo2Real: Task Arithmetic for Pseudo-Label Correction in Automatic SpeechRecognition

Paperium

Oct 29

Pseudo2Real: Task Arithmetic for Pseudo-Label Correction in Automatic SpeechRecognition

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for ReviewerToo: Should AI Join The Program Committee? A Look At The Future of PeerReview

Paperium

Oct 29

ReviewerToo: Should AI Join The Program Committee? A Look At The Future of PeerReview

#ai #deeplearning #computerscience #machinelearning

2 min read

Cover image for Dyna-Mind: Learning to Simulate from Experience for Better AI Agents

Paperium

Oct 29

Dyna-Mind: Learning to Simulate from Experience for Better AI Agents

#ai #deeplearning #computerscience #machinelearning

2 min read

Cover image for Which Heads Matter for Reasoning? RL-Guided KV Cache Compression

Paperium

Oct 29

Which Heads Matter for Reasoning? RL-Guided KV Cache Compression

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation viaExecution

Paperium

Oct 29

BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation viaExecution

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs

Paperium

Oct 29

PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for MRMR: A Realistic and Expert-Level Multidisciplinary Benchmark forReasoning-Intensive Multimodal Retrieval

Paperium

Oct 29

MRMR: A Realistic and Expert-Level Multidisciplinary Benchmark forReasoning-Intensive Multimodal Retrieval

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for StatEval: A Comprehensive Benchmark for Large Language Models in Statistics

Paperium

Oct 28

StatEval: A Comprehensive Benchmark for Large Language Models in Statistics

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for Progressive Gaussian Transformer with Anisotropy-aware Sampling for OpenVocabulary Occupancy Prediction

Paperium

Oct 28

Progressive Gaussian Transformer with Anisotropy-aware Sampling for OpenVocabulary Occupancy Prediction

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for Bridging Reasoning to Learning: Unmasking Illusions using Complexity Out ofDistribution Generalization

Paperium

Oct 28

Bridging Reasoning to Learning: Unmasking Illusions using Complexity Out ofDistribution Generalization

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for DISCO: Diversifying Sample Condensation for Efficient Model Evaluation

Paperium

Oct 28

DISCO: Diversifying Sample Condensation for Efficient Model Evaluation

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for KORMo: Korean Open Reasoning Model for Everyone

Paperium

Oct 28

KORMo: Korean Open Reasoning Model for Everyone

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level EntropyShaping

Paperium

Oct 28

ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level EntropyShaping

#ai #deeplearning #computerscience #machinelearning

1 min read

Cover image for Don't Waste Mistakes: Leveraging Negative RL-Groups via Confidence Reweighting

Paperium

Oct 28

Don't Waste Mistakes: Leveraging Negative RL-Groups via Confidence Reweighting

#ai #deeplearning #computerscience #machinelearning

1 min read