Towards flexible perception with visual memory discuss: https://
huggingface.co/papers/2408.08
172
… Training a neural network is a monolithic endeavor, akin to carving knowledge into stone: once the process is completed, editing the knowledge in a network is nearly impossible, since all
@_akhaliq
-
Flexible Perception with Visual Memory: Beyond Monolithic Neural Networks
By
–
-
PeriodWave-Turbo: High-Fidelity Waveform Generation via Flow Matching
By
–
Accelerating High-Fidelity Waveform Generation via Adversarial Flow Matching Optimization discussion: https://
huggingface.co/papers/2408.08
019
… This paper introduces PeriodWave-Turbo, a high-fidelity and high-efficient waveform generation model via adversarial flow matching optimization. -
MVInpainter: Multi-View Consistent Inpainting for 2D and 3D Editing
By
–
MVInpainter
— AK (@_akhaliq) 16 août 2024
Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editing
discuss: https://t.co/2GHE1AiMSw
Novel View Synthesis (NVS) and 3D generation have recently achieved prominent improvements. However, these works mainly focus on confined categories or synthetic… pic.twitter.com/qJybCtfRTdMVInpainter Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editing discuss: https://
huggingface.co/papers/2408.08
000
… Novel View Synthesis (NVS) and 3D generation have recently achieved prominent improvements. However, these works mainly focus on confined categories or synthetic -
DeepSeek-Prover-V1.5: Advanced Theorem Proving with Reinforcement Learning
By
–
DeepSeek-Prover-V1.5 Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search discuss: https://
huggingface.co/papers/2408.08
152
… We introduce DeepSeek-Prover-V1.5, an open-source language model designed for theorem proving in Lean 4, which enhances -
FancyVideo: Dynamic Consistent Video Generation with Cross-frame Textual Guidance
By
–
FancyVideo
— AK (@_akhaliq) 16 août 2024
Towards Dynamic and Consistent Video Generation via Cross-frame Textual Guidance
discuss: https://t.co/LeiUEc7Pvc
Synthesizing motion-rich and temporally consistent videos remains a challenge in artificial intelligence, especially when dealing with extended… pic.twitter.com/5Ds7jMBMZEFancyVideo Towards Dynamic and Consistent Generation via Cross-frame Textual Guidance discuss: https://
huggingface.co/papers/2408.08
189
… Synthesizing motion-rich and temporally consistent videos remains a challenge in artificial intelligence, especially when dealing with extended -
Software Engineering Agents Expertise Integration Presentation Broadcast
By
–
.@kexun_zhang presented Integrating Expertise of Software Engineering Agents live today
— AK (@_akhaliq) 15 août 2024
see the broadcast here: https://t.co/lPSJrbRBMF.
@kexun_zhang presented Integrating Expertise of Software Engineering Agents live today see the broadcast here: -
Generative Photomontage: Controlling Text-to-Image Generation
By
–
Generative Photomontage discussion: https://
huggingface.co/papers/2408.07
116
… Text-to-image models are powerful tools for image creation. However, the generation process is akin to a dice roll and makes it difficult to achieve a single image that captures everything a user wants. In this paper, -
InfinityMATH: Scalable Dataset for Mathematical Reasoning
By
–
InfinityMATH A Scalable Instruction Tuning Dataset in Programmatic Mathematical Reasoning discussion: https://
huggingface.co/papers/2408.07
089
… Recent advancements in Chain-of-Thoughts (CoT) and Program-of-Thoughts (PoT) methods have greatly enhanced language models' mathematical reasoning -
Salesforce releases DEI AI software engineering agents with 55% resolve rate
By
–
Salesforce releases DEI, an open AI software engineering agents org with a 55% resolve rate on SWE-Bench Lite Discussion:
https://
huggingface.co/papers/2408.07
060
… We propose DEI (Diversity Empowered Intelligence), a framework that leverages SWE agents' unique expertise. DEI functions as a -
LongWriter: 10,000+ Word Generation from Long Context LLMs
By
–
New from @thukeg LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs author @realYushiBai is active in discussion section to answer your questions: https://
huggingface.co/papers/2408.07
055
…