GRLO: Towards Generalizable Reinforcement Learning in Open-Ended Environments from Zero
An AI research paper on GRLO: Towards Generalizable Reinforcement Learning in Open-Ended Environments from Zero.
Engineering 5.0 · Research 7.0 · Business 4.0
aipentium - AI Papers with Code, Datasets and Engineering Notes
aipentium: browse curated AI and robotics papers about humanoid robots, embodied AI, robot manipulation, VLA models, Diffusion Policy, Sim2Real and robot foundation models.
Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs
An AI research paper on Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs.
Engineering 5.0 · Research 7.0 · Business 4.0
EvoNav: Evolutionary Reward Function Design for Robot Navigation with Large Language Models
An AI research paper on EvoNav: Evolutionary Reward Function Design for Robot Navigation with Large Language Models.
Engineering 5.0 · Research 7.0 · Business 4.0
Semantic Reward Collapse and the Preservation of Epistemic Integrity in Adaptive AI Systems
An AI research paper on Semantic Reward Collapse and the Preservation of Epistemic Integrity in Adaptive AI Systems.
Engineering 5.0 · Research 7.0 · Business 4.0
Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators
An AI research paper on Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators.
Engineering 5.0 · Research 7.0 · Business 4.0
$ξ$-DPO: Direct Preference Optimization via Ratio Reward Margin
An AI research paper on $ξ$-DPO: Direct Preference Optimization via Ratio Reward Margin.
Engineering 5.0 · Research 7.0 · Business 4.0
Implicit Preference Alignment for Human Image Animation
An AI research paper on Implicit Preference Alignment for Human Image Animation.
Engineering 5.0 · Research 7.0 · Business 4.0
Beyond Pairs: Your Language Model is Secretly Optimizing a Preference Graph
An AI research paper on Beyond Pairs: Your Language Model is Secretly Optimizing a Preference Graph.
Engineering 5.0 · Research 7.0 · Business 4.0
MultiSoc-4D: A Benchmark for Diagnosing Instruction-Induced Label Collapse in Closed-Set LLM Annotation of Bengali Social Media
An AI research paper on MultiSoc-4D: A Benchmark for Diagnosing Instruction-Induced Label Collapse in Closed-Set LLM Annotation of Bengali Social Media.
Engineering 5.0 · Research 7.0 · Business 4.0
Optimal Transport for LLM Reward Modeling from Noisy Preference
An AI research paper on Optimal Transport for LLM Reward Modeling from Noisy Preference.
Engineering 5.0 · Research 7.0 · Business 4.0
Mitigating Cognitive Bias in RLHF by Altering Rationality
An AI research paper on Mitigating Cognitive Bias in RLHF by Altering Rationality.
Engineering 5.0 · Research 7.0 · Business 4.0
$f$-Divergence Regularized RLHF: Two Tales of Sampling and Unified Analyses
An AI research paper on $f$-Divergence Regularized RLHF: Two Tales of Sampling and Unified Analyses.
Engineering 5.0 · Research 7.0 · Business 4.0
Not All That Is Fluent Is Factual: Investigating Hallucinations of Large Language Models in Academic Writing
An AI research paper on Not All That Is Fluent Is Factual: Investigating Hallucinations of Large Language Models in Academic Writing.
Engineering 5.0 · Research 7.0 · Business 4.0
Efficiently Aligning Language Models with Online Natural Language Feedback
An AI research paper on Efficiently Aligning Language Models with Online Natural Language Feedback.
Engineering 5.0 · Research 7.0 · Business 4.0
Efficient Preference Poisoning Attack on Offline RLHF
An AI research paper on Efficient Preference Poisoning Attack on Offline RLHF.
Engineering 5.0 · Research 7.0 · Business 4.0
Investigating LLM's Problem Solving Capability -- a Study on Statics Questions
An AI research paper on Investigating LLM's Problem Solving Capability -- a Study on Statics Questions.
Engineering 5.0 · Research 7.0 · Business 4.0
HealthBench Professional: Evaluating Large Language Models on Real Clinician Chats
An AI research paper on HealthBench Professional: Evaluating Large Language Models on Real Clinician Chats.
Engineering 5.0 · Research 7.0 · Business 4.0
Construction of a Battery Research Knowledge Graph using a Global Open Catalog
An AI research paper on Construction of a Battery Research Knowledge Graph using a Global Open Catalog.
Engineering 5.0 · Research 7.0 · Business 4.0
IceBreaker for Conversational Agents: Breaking the First-Message Barrier with Personalized Starters
An AI research paper on IceBreaker for Conversational Agents: Breaking the First-Message Barrier with Personalized Starters.
Engineering 5.0 · Research 7.0 · Business 4.0
The impact of postediting on AI generative translation in Yemeni context: Translating literary prose by ChatGPT
An AI research paper on The impact of postediting on AI generative translation in Yemeni context: Translating literary prose by ChatGPT.
Engineering 5.0 · Research 7.0 · Business 4.0