Lingfeng Shen
@Lingfeng_nlp
Followers
525
Following
2K
Media
30
Statuses
298
An #LLM researcher at Bytedance Seed, a trader, and a @MercedesAMGF1 Fan!
Saratoga, CA
Joined February 2020
Intelligence is not the ability to remember the past. Intelligence is not the ability to react to the present. The best definition of intelligence is the ability to predict the future!
1
0
9
Peter Thiel today: “Boomers are strangely uncurious about how the world is not really working for their kids. It’s always hard to know how much bad faith there is or how bad the actors are. I think it’s odd that people thought it was odd that I was complaining about student debt
638
1K
11K
How to start a business on @Polymarket 101 The origin of the new garage-band market-maker 🧵
15
29
272
How can we boost LLM agents’ generalizability to OOD tasks and environments? Check out CodeGym, our new project for synthesizing environments for LLM agent RL training. CodeGym is a synthetic environment generation framework for reinforcement learning on multi-turn tool-use
3
6
12
Markets on everything. We’re proud to announce that $ICE, the owner of @NYSE and the largest exchange company in the world, is making a strategic investment of $2 billion into Polymarket, valuing us at $9 billion post-money. Our partnership with ICE marks a major step in
1K
1K
12K
Rule #1 Never trust the opinion of anyone who is involved in politics. This guy spent the last year licking the heels of Trump and pushing his agenda, only for him to totally 180 on everything because he didn’t get favored in that bill. What a beautiful world we live in.
1
1
10
1. Lehman. Wells Fargo prop lost hundreds of millions of dollars on converts, bond basis and levered loans. Head of the desk went to the board and asked for $4 billion in balance sheet to buy everything in sight, got it, because Wells was in good shape. Better lucky than good.
@bennpeifert Your top 5 formative trading days/events where you learned the most.
33
47
1K
Trump says the Fed chair is a “major loser,” but the bigger loser from his fracas with the Fed could be whomever Trump chooses to succeed Jay Powell next year By bashing the Fed to influence policy, Trump could create a “shadow of suspicion” over his own nominee
42
76
513
Finally Someone Looks at the ODTE IRON CONDORS.... In ODTE 3 minutes makes a big difference.. S&P 500 Index (SPX) iron condors executed on zero-days-to-expiration (0DTE) contracts at 3:55 PM EST and 3:58 PM EST, respectively. The evaluation period spans January 2013 through
10
11
80
JUST NOW: Rep Steven Horsford GRILLS Jamieson Greer on Donald Trump’s tariff reversal: “Is this market manipulation? If it’s not market manipulation, what is it? Who’s benefiting? What billionaire just got richer?”
1K
10K
40K
Do You Have A Soul? If we assume that people have eternal souls, where was your soul before life began or when only a single organism existed? Buddhism teaches that there is no fixed, eternal self (anatta). Instead of a soul, we are a continuous process—just a chain of causes
5
6
63
There is no such thing as alpha. Most hedge fund managers were simply in the right place at the right time, found a temporary, repetitive pattern, and rode it all the way up—mistaking it for skill or intelligence. For the lucky ones, the pattern lasted a few more years than for
43
41
431
Why Do I Get Angry When I Am Insulted Q: Why do I get angry when someone insults me? A: Because a part of you wonders if the insult might be true. Q: That’s not true. If a stranger calls me stupid, that doesn’t mean I’m stupid. A: But it also doesn’t prove that you’re not. Q:
10
8
103
Looking for a better way to fuse speech and text modality with pre-trained large language models? Check out our paper: SSR: Alignment-Aware Modality Connector for Speech Language Models 💡 🔗 https://t.co/d28Ew0yYzb
#SpeechLM #ModalityFusion
3
9
40
Low-resource, high-risk: A @JohnsHopkins study (feat. @DanielKhashabi, @Lingfeng_nlp, @weiting_nlp, @YunmoChen, @jackjingyuzhang, @fe1ixxu, & more) finds that #AI text generators are more likely to create harmful content in certain languages. Learn more: https://t.co/vEEaKEovyK
2
10
15
我们离理想的AutoGPT还有多远？[1/4] AutoGPT[1]已经163k star了，AutoGPT的开发者雕花了一年多，但它仍然停留在demo阶段，算不上产品（即使面向开发者)。这和传统开源软件的发展轨迹相差甚远，核心原因是Agent的上限由底座模型决定
20
52
276
Here’s some better news: Combining CPO and SimPO can likely improve the model! Check out more details in our GitHub code: https://t.co/9l63ukeSTe
We recently had multiple rounds of discussions with the SimPO authors regarding the lack of comparison to CPO in their main paper. We both agree that it was an unintentional oversight, and they will update the paper to address it. We appreciate their positive and prompt response
1
14
38
Will be presenting my work on LLM-MT at #naacl today, at In-Person Poster Session 7 (11am). Please come if you are interested in machien translation and multilinguality! Would also love to discuss multimodal LLM (speech + text) and non-autoregressive decoding (NAT, diffusion)!
📚 LLMs benefit from demonstrations, but can we make zero-shot translations better without access to parallel corpora? Find out how we bridge the gap between zero- and few-shot translation with only monolingual information in our latest paper! 🤓 https://t.co/ehtAKISr44
@jhuclsp
0
5
15
So happy to work on this project with @TaimingLu, @Xinyu2ML, @weiting_nlp, @BeidiChen, and @HuaxiuYaoML. Thanks to my amazing collaborators! 🤗
0
0
4