Top Tweets for #RewardModels
This work was a part of my time at @IBMResearch as an intern.
Huge thanks to my co-authors!
Shubham Gandhi (@shubhamrgandhi), Jason Tsay (@jsntsay), Jatin Ganhotra (@JatinGanhotra ), Kiran Kate, Yara Rizk (@serialorganizer)
#NeurIPS2025 #LLMAgents #RewardModels #AIForCode
Beyond the Black Box: Three Lethal Ideas Reshaping AI in 2025 https://t.co/jIhUnGhJc2 via @ClickInsights #AgenticAI #rewardmodels #AITraining #DeconstructingAI #CoreAnalytics #AItrends
Thrilled to share that my work(w/ Manjunatha Naik) on "RMA: Reward Model Alignment with Human Preference" has been accepted at the ICML World of Models Workshop 2025!
More details about the work are present here: https://t.co/RHUqWaDozQ
#icml2025 #Rewardmodels
What To Know About Delayed Gratification https://t.co/0K3Vsk8B8p
#DelayedGratification #Gratification #Reward #RewardModels #Rewards
Check out the latest from our #AIResearch team, in this fascinating blog written by our own @kolbytn. #syntheticdata #DPO #rewardmodels #aigaming
AI Reward Models: Trustworthy or Not?
#RewardModels #BeamSearch #AI #ArtificialIntelligence #MachineLearning #DeepLearning #Efficiency #Reliability #TechDiscussion #Programming
@BrettRegen50025 @Carolataylor01 @creator_links I'm equally eager for our meeting next week to delve into the synergy between innovative reward models and sustainable tokenomics. Let's build a thriving Web3 gaming ecosystem! 🚀✨ #Web3Gaming #SustainableEcosystem #RewardModels #Collaboration
https://t.co/rJy91O3PK2 provided a great benchmark and collection of #rewardmodels. But are there good Reward models for tasks like. -- Coding, Reasoning, Mathematical Puzzles, etc ?? @natolambert @BanghuaZ @rm_rafailov
@ericmitchellai @yumeng0818 @vwxyzjn @g_k_swamy
#RewardModels
🔥LLM Reasoners🔥 now supports advanced 🏆reward models (RM)🏆 to boost LLM reasoning!
Check out the 1st example based on Eurux-RM: https://t.co/74bwqQkT8Z
🚀It easily boosts #llama3 8B from 0.49 to 0.73 on GSM8K
👉Eurux paper https://t.co/cwEeidbwjM
5. Dual Reward Models
It uses two separate reward models - one optimized for helpfulness and the other for safety.
This approach strikes a balance, avoiding the safety-helpfulness tradeoff identified in previous works.
#RewardModels
Last Seen Hashtags on Sotwe
معصيتي_رحتي
Seen from Saudi Arabia
figurebukkake
Seen from Singapore
Killthebeat
Seen from United States
หาหญิงเดี่ยวFwbตัวเมืองเพชร
Seen from Thailand
bôchapô
Seen from United States
bocilsd
Seen from France
محنه
Seen from Italy
LiverAnd
Seen from Argentina
mouthfisting
Seen from United States
roblox rule34
Seen from Malaysia
Trends for you
Most Popular Users
Elon Musk 
@elonmusk
240.1M followers
Barack Obama
@barackobama
119.3M followers
Donald J. Trump
@realdonaldtrump
111.6M followers
Cristiano Ronaldo
@cristiano
108.8M followers
Narendra Modi
@narendramodi
107M followers
Rihanna
@rihanna
97.2M followers
NASA
@nasa
92.1M followers
Justin Bieber
@justinbieber
90.5M followers
KATY PERRY
@katyperry
86.7M followers
Taylor Swift
@taylorswift13
80.5M followers
Lady Gaga
@ladygaga
72.1M followers
Kim Kardashian
@kimkardashian
69.4M followers
YouTube
@youtube
68.6M followers
Virat Kohli
@imvkohli
68.4M followers
Bill Gates
@billgates
63.4M followers
The Ellen Show
@theellenshow
62.5M followers
CNN
@cnn
61.9M followers
Neymar Jr
@neymarjr
61M followers
X
@x
60.9M followers
CNN Breaking News
@cnnbrk
59.9M followers