Content Feed

The latest content from across the network

Ranked Latest Top this week
[2603.26571] Generation Is Compression: Zero-Shot Video Coding via Stochastic Rectified Flow
Machine Learning

[2603.26571] Generation Is Compression: Zero-Shot Video Coding via Stochastic Rectified Flow

Abstract page for arXiv paper 2603.26571: Generation Is Compression: Zero-Shot Video Coding via Stochastic Rectified Flow

arXiv - AI · 3 min ·
[2603.26539] How Open Must Language Models be to Enable Reliable Scientific Inference?
Llms

[2603.26539] How Open Must Language Models be to Enable Reliable Scientific Inference?

Abstract page for arXiv paper 2603.26539: How Open Must Language Models be to Enable Reliable Scientific Inference?

arXiv - AI · 3 min ·
[2603.26542] The Multi-AMR Buffer Storage, Retrieval, and Reshuffling Problem: Exact and Heuristic Approaches
Nlp

[2603.26542] The Multi-AMR Buffer Storage, Retrieval, and Reshuffling Problem: Exact and Heuristic Approaches

Abstract page for arXiv paper 2603.26542: The Multi-AMR Buffer Storage, Retrieval, and Reshuffling Problem: Exact and Heuristic Approaches

arXiv - AI · 4 min ·
[2603.26498] Rocks, Pebbles and Sand: Modality-aware Scheduling for Multimodal Large Language Model Inference
Llms

[2603.26498] Rocks, Pebbles and Sand: Modality-aware Scheduling for Multimodal Large Language Model Inference

Abstract page for arXiv paper 2603.26498: Rocks, Pebbles and Sand: Modality-aware Scheduling for Multimodal Large Language Model Inference

arXiv - AI · 4 min ·
[2603.26425] CPUBone: Efficient Vision Backbone Design for Devices with Low Parallelization Capabilities
Machine Learning

[2603.26425] CPUBone: Efficient Vision Backbone Design for Devices with Low Parallelization Capabilities

Abstract page for arXiv paper 2603.26425: CPUBone: Efficient Vision Backbone Design for Devices with Low Parallelization Capabilities

arXiv - AI · 4 min ·
[2603.26515] JAL-Turn: Joint Acoustic-Linguistic Modeling for Real-Time and Robust Turn-Taking Detection in Full-Duplex Spoken Dialogue Systems
Llms

[2603.26515] JAL-Turn: Joint Acoustic-Linguistic Modeling for Real-Time and Robust Turn-Taking Detection in Full-Duplex Spoken Dialogue Systems

Abstract page for arXiv paper 2603.26515: JAL-Turn: Joint Acoustic-Linguistic Modeling for Real-Time and Robust Turn-Taking Detection in ...

arXiv - AI · 4 min ·
[2603.26458] Can AI Models Direct Each Other? Organizational Structure as a Probe into Training Limitations
Machine Learning

[2603.26458] Can AI Models Direct Each Other? Organizational Structure as a Probe into Training Limitations

Abstract page for arXiv paper 2603.26458: Can AI Models Direct Each Other? Organizational Structure as a Probe into Training Limitations

arXiv - AI · 4 min ·
[2603.26330] Mitigating the Reasoning Tax in Vision-Language Fine-Tuning with Input-Adaptive Depth Aggregation
Llms

[2603.26330] Mitigating the Reasoning Tax in Vision-Language Fine-Tuning with Input-Adaptive Depth Aggregation

Abstract page for arXiv paper 2603.26330: Mitigating the Reasoning Tax in Vision-Language Fine-Tuning with Input-Adaptive Depth Aggregation

arXiv - AI · 3 min ·
[2603.26410] Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models
Machine Learning

[2603.26410] Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models

Abstract page for arXiv paper 2603.26410: Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens...

arXiv - AI · 4 min ·
[2603.26348] Reflect to Inform: Boosting Multimodal Reasoning via Information-Gain-Driven Verification
Llms

[2603.26348] Reflect to Inform: Boosting Multimodal Reasoning via Information-Gain-Driven Verification

Abstract page for arXiv paper 2603.26348: Reflect to Inform: Boosting Multimodal Reasoning via Information-Gain-Driven Verification

arXiv - AI · 3 min ·
[2603.26323] From Human Cognition to Neural Activations: Probing the Computational Primitives of Spatial Reasoning in LLMs
Llms

[2603.26323] From Human Cognition to Neural Activations: Probing the Computational Primitives of Spatial Reasoning in LLMs

Abstract page for arXiv paper 2603.26323: From Human Cognition to Neural Activations: Probing the Computational Primitives of Spatial Rea...

arXiv - AI · 4 min ·
[2603.26359] Automated near-term quantum algorithm discovery for molecular ground states
Llms

[2603.26359] Automated near-term quantum algorithm discovery for molecular ground states

Abstract page for arXiv paper 2603.26359: Automated near-term quantum algorithm discovery for molecular ground states

arXiv - AI · 3 min ·
[2603.26332] CALRK-Bench: Evaluating Context-Aware Legal Reasoning in Korean Law

[2603.26332] CALRK-Bench: Evaluating Context-Aware Legal Reasoning in Korean Law

Abstract page for arXiv paper 2603.26332: CALRK-Bench: Evaluating Context-Aware Legal Reasoning in Korean Law

arXiv - AI · 3 min ·
[2603.26324] PRISMA: Toward a Normative Information Infrastructure for Responsible Pharmaceutical Knowledge Management
Nlp

[2603.26324] PRISMA: Toward a Normative Information Infrastructure for Responsible Pharmaceutical Knowledge Management

Abstract page for arXiv paper 2603.26324: PRISMA: Toward a Normative Information Infrastructure for Responsible Pharmaceutical Knowledge ...

arXiv - AI · 4 min ·
[2603.26285] PhysVid: Physics Aware Local Conditioning for Generative Video Models
Machine Learning

[2603.26285] PhysVid: Physics Aware Local Conditioning for Generative Video Models

Abstract page for arXiv paper 2603.26285: PhysVid: Physics Aware Local Conditioning for Generative Video Models

arXiv - AI · 3 min ·
[2603.26292] findsylls: A Language-Agnostic Toolkit for Syllable-Level Speech Tokenization and Embedding
Llms

[2603.26292] findsylls: A Language-Agnostic Toolkit for Syllable-Level Speech Tokenization and Embedding

Abstract page for arXiv paper 2603.26292: findsylls: A Language-Agnostic Toolkit for Syllable-Level Speech Tokenization and Embedding

arXiv - AI · 3 min ·
[2603.26270] Knowdit: Agentic Smart Contract Vulnerability Detection with Auditing Knowledge Summarization
Machine Learning

[2603.26270] Knowdit: Agentic Smart Contract Vulnerability Detection with Auditing Knowledge Summarization

Abstract page for arXiv paper 2603.26270: Knowdit: Agentic Smart Contract Vulnerability Detection with Auditing Knowledge Summarization

arXiv - AI · 4 min ·
[2603.26260] GeoGuide: Hierarchical Geometric Guidance for Open-Vocabulary 3D Semantic Segmentation
Machine Learning

[2603.26260] GeoGuide: Hierarchical Geometric Guidance for Open-Vocabulary 3D Semantic Segmentation

Abstract page for arXiv paper 2603.26260: GeoGuide: Hierarchical Geometric Guidance for Open-Vocabulary 3D Semantic Segmentation

arXiv - AI · 4 min ·
[2603.26259] Working Notes on Late Interaction Dynamics: Analyzing Targeted Behaviors of Late Interaction Models
Machine Learning

[2603.26259] Working Notes on Late Interaction Dynamics: Analyzing Targeted Behaviors of Late Interaction Models

Abstract page for arXiv paper 2603.26259: Working Notes on Late Interaction Dynamics: Analyzing Targeted Behaviors of Late Interaction Mo...

arXiv - AI · 3 min ·
[2603.26248] Automatic Speech Recognition for Documenting Endangered Languages: Case Study of Ikema Miyakoan

[2603.26248] Automatic Speech Recognition for Documenting Endangered Languages: Case Study of Ikema Miyakoan

Abstract page for arXiv paper 2603.26248: Automatic Speech Recognition for Documenting Endangered Languages: Case Study of Ikema Miyakoan

arXiv - AI · 3 min ·