· ai
Delty (YC X25) Is Hiring an ML Engineer
Article URL: https://www.ycombinator.com/companies/delty/jobs/MDeC49o-machine-learning-engineer Comments URL: https://news.ycombinator.com/item?id=46318676 Poin...
-
- · ai
[Paper] Differences That Matter: Auditing Models for Capability Gap Discovery and Rectification
Conventional evaluation methods for multimodal LLMs (MLLMs) lack interpretability and are often insufficient to fully disclose significant capability gaps acros...
- · ai
[Paper] DVGT: Driving Visual Geometry Transformer
Perceiving and reconstructing 3D scene geometry from visual inputs is crucial for autonomous driving. However, there still lacks a driving-targeted dense geomet...
- · ai
[Paper] EasyV2V: A High-quality Instruction-based Video Editing Framework
While image editing has advanced rapidly, video editing remains less explored, facing challenges in consistency, control, and generalization. We study the desig...
- · ai
[Paper] Generative Adversarial Reasoner: Enhancing LLM Reasoning with Adversarial Reinforcement Learning
Large language models (LLMs) with explicit reasoning capabilities excel at mathematical reasoning yet still commit process errors, such as incorrect calculation...
- · ai
[Paper] Exploration v.s. Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward
This paper examines the exploration-exploitation trade-off in reinforcement learning with verifiable rewards (RLVR), a framework for improving the reasoning of ...
- · ai
[Paper] Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning
Standard practice across domains from robotics to language is to first pretrain a policy on a large-scale demonstration dataset, and then finetune this policy, ...
- · ai
[Paper] SFTok: Bridging the Performance Gap in Discrete Tokenizers
Recent advances in multimodal models highlight the pivotal role of image tokenization in high-resolution image generation. By compressing images into compact la...
- · ai
[Paper] Flowing from Reasoning to Motion: Learning 3D Hand Trajectory Prediction from Egocentric Human Interaction Videos
Prior works on 3D hand trajectory prediction are constrained by datasets that decouple motion from semantic supervision and by models that weakly link reasoning...
- · ai
[Paper] In-Context Algebra
We investigate the mechanisms that arise when transformers are trained to solve arithmetic on sequences where tokens are variables whose meaning is determined o...
- · ai
[Paper] Impacts of Racial Bias in Historical Training Data for News AI
AI technologies have rapidly moved into business and research applications that involve large text corpora, including computational journalism research and news...
- · ai
[Paper] LinkedOut: Linking World Knowledge Representation Out of Video LLM for Next-Generation Video Recommendation
Video Large Language Models (VLLMs) unlock world-knowledge-aware video understanding through pretraining on internet-scale data and have already shown promise o...