AllyshipContent Radar

News 2859

Chủ đề cộng đồng đang thảo luận

Crawl live-1795115700000 · 02:15 20 thg 11, 2026 · Xuất bản 02:31 20 thg 11, 2026

206 / 2859 chủ đề đạt ngưỡng 55 trong khoảng này.

181

When we shared our journey about becoming a Self Driving Company, I shared a couple examples of "loops" Engineers built to complete long-desired migrations or drive translation work across the product

56

2 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

stkenned, nikhilgoyalai 0 bài viết · X
Nguyên văn nguồn
Chi tiết nguồn

When we shared our journey about becoming a Self Driving Company, I shared a couple examples of "loops" Engineers built to complete long-desired migrations or drive translation work across the product in record time. Back then, they were a bit hard to set up. It took an engineer dedicating time. Now, we're built it as "Missions" into Replit itself. All you need to do is describe your goal and send a swarm of Agents to accomplish it! Optimize your marketing content, migrate off that legacy database, overhaul your design system. Agents work tirelessly, they just need the right visionary to send them in the right direction. That's you. https://replit.com/blog/introducing-replit-missions

182

Ask HN: Anyone else blurting?

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 17 tương tác đã đo · Nguồn crawl

l33tbro 1 bài viết · HN: LLM
Nguyên văn nguồn
Chi tiết nguồn

Like most, I was stoked on LLMs when they became available. Particularly on the earlier free tiers where the slightly questionable answers were offset by generous tokens. Now, I'm finding that having to use this tech is becoming much less fun. The constant corrections, the constant prompting for greater brevity, the grating certainty and sycophancy. Others probably are forgiving considering the net benefit. But for me it honestly now feels like a chore, which is reflected in how my frustration is now appearing in how I communicate to it now. Instead of articulating and making my prompts precise, I'm just straight-out blurting. Typos, missed words, poor semantic structure - I guess I maybe at some point reasoned that "it will get the picture, so why waste effort being articulate?" Or maybe I'm just anticipating that it is going to get it 15 percent wrong, so why even try and be articulate. Just blurt and steer. Blurt and steer. Is anyone else finding this? I actually sometimes worry about it. I feel it's not just the fact that I'm offloading my cognition to it that is making me dumber, it is the way I'm communicating with it. They say the act of writing is tied to the act of thinking, and my prompts are basicslly the typographic equivalent of grunting right now.

183

Launch HN: StarSling (YC P25) – Self-improving CI for agent-volume repos

62

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 137 tương tác đã đo · Nguồn crawl

yonasb 1 bài viết · HN: AI agent
Nguyên văn nguồn
Chi tiết nguồn

We’re Yonas and Daniel and we’re building StarSling ( https://starsling.dev ), fast GitHub Actions runners with AI agents that ship PRs to continuously improve your tests and workflows. Every CI job gets its own ephemeral sandbox on the fastest Zen 5 machines and NVMe Disk with unlimited concurrency so a burst of agent PRs all run at once. We’re different from other runners because ours come with agents that cut down your CI bill over time. PRs are generated through our CI harness, which runs an agent loop that’s tuned to improve your CI speed and reduce cost. Mastra now merges over 1,800 PRs a month and we got their slowest workflow from 29m 56s on GitHub-hosted runners down to 5m 06s (5.87x) on StarSling. We realized the true value of having an agent loop running on top of fast runners when our agents found an 11-month-old performance bottleneck in better-auth. The fix made one of their test jobs 5.4x faster: https://github.com/better-auth/better-auth/pull/10762 . I previously founded StackShare, which grew to over 1.5M developers. Daniel helped build Netflix's internal developer portal. Last year we started building AI agents for DevOps because shipping code to prod fell way behind agentic coding. We hit the CI bottleneck ourselves as we were building agents. Our own agents shipped so many PRs that at peak our job queues were backed up for hours and our CI bill got close to our inference bill. We now support per-second billing, and just shipped StarSling Disks - persistent disks that give you a 4.9x speedup in dependencies ready over actions/cache. You can see a quick demo of disks in action here : https://www.youtube.com/watch?v=2JrrpRm9Mww . Our CI harness runs a loop that has agents: - Analyze your workflows, run logs, and machine telemetry - Propose an optimization - Test your unchanged workflow side by side the proposed change - Deterministically judge that the difference is statistically significant - Ship the winner to you as a PR with benchmarks evidence We benchmarked open source repos on our runners and average 10x speedup in wall clock time with 70% less runner time: - https://github.com/starsling-demo-org/benchmark-gogs (12.8x) - https://github.com/starsling-demo-org/benchmark-shellcheck (5.5x) - https://github.com/starsling-demo-org/benchmark-chatwoot (3.9x) - https://github.com/starsling-demo-org/benchmark-transfer.sh (11.7x) - https://github.com/starsling-demo-org/benchmark-mirotalksfu (36.4x) Yes, you can do these optimizations yourself with prompts so we’ve released skills for this: https://github.com/starslingdev/skills . The benefit of using our agents is that you don’t need to spend tokens and CI compute finding optimizations yourself. We started building our runners on AWS at the beginning of the year and realized that was too expensive. But at that time there weren’t any cloud providers that could give us the same machines we were getting on AWS, billed per minute (microVMs). So we convinced a handful of sandbox providers to get Zen 5s and started benchmarking them publicly ( https://github.com/starslingdev/hpc-sandbox-benchmarks ). We’ve learned that fast infrastructure is table stakes for CI, but it’s not sufficient on its own. To get fast and cost effective CI you need a process that continues making improvements. We turned CI optimizations from OpenAI, Anthropic, Linear and others into playbooks for your agent: https://starsling.dev/ci-playbooks . To try it, give your agent this URL: https://docs.starsling.dev/start . You get 2,000 free minutes. Our agents start opening PRs once you've hit about 10,000 minutes. Today we announced our CI Challenge: if StarSling can't save you at least 10% on your next CI bill, we'll literally give you $1,000. Eligibility and rules here: https://starsling.dev/blog/ci-challenge . We’d love your feedback on the headless experience and what you’d like to see improved in your own CI setup! https://starsling.dev

184

MAI Code 2 and Code 2 Flash

66

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 592 tương tác đã đo · Nguồn crawl

lemonish97 1 bài viết · HN: LLM
Nguyên văn nguồn
Chi tiết nguồn
185

Introducing GPT-6.2 Astra and Sol

71

3 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · chưa có số tương tác · Nguồn crawl

OpenAI, chatgpt và 1 nguồn khác 1 bài viết · OpenAI News, X
Nguyên văn nguồn
Chi tiết nguồn

Introducing GPT‑6.2 Astra and Sol, with better professional outputs, coding, computer use, and efficiency at lower cost across ChatGPT Work, Codex, and the API.

186

Not Everything Needs an LLM

63

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 261 tương tác đã đo · Nguồn crawl

speckx 1 bài viết · HN: LLM
Nguyên văn nguồn
Chi tiết nguồn
187

Put Gemini to work for you

63

2 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · chưa có số tương tác · Nguồn crawl

Josh Woodward, joshwoodward 1 bài viết · Google AI, X
Nguyên văn nguồn
Chi tiết nguồn

<img src="https://storage.googleapis.com/gweb-uniblog-publish-prod/images/Hero_2784_x_1566.max-600x600.format-webp.webp">Tasks in Gemini is now free of charge in six countries, with new features starting in the U.S. and deeper Google Workspace integration to get things done on your behalf.

188

Show HN: TrnRT – An open-source LLM inference engine for AWS Trainium

59

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 61 tương tác đã đo · Nguồn crawl

sanchitmonga22 1 bài viết · HN: open weights
Nguyên văn nguồn
Chi tiết nguồn

Hi HN, Sanchit here from RunAnywhere (YC W26). We just open-sourced TrnRT: Trainium RunTime, our inference engine for AWS Trainium. We started 3 weeks back, and currently we’re able to serve and run GLM 5.3 flash (FP8) on AWS trn2.48xlarge, and will bring more models support soon. It’s open to contributions :) What it does today: - Serves 2 instances of GLM-5.3 flash on a single box, 8 trn2 with a cache aware router. - Can process 3.57M TPM (tokens per minute) on SemiAnalysis's AgentX benchmarks. - Runs decode as one NKI kernel per layer half, or for the 11 sparse-attention layers fuses both blocks into a single kernel, for faster performance. We started working on Trn2 because we wanted to explore it and see if we can come close to beating it’s performance in terms of cost efficiency compared to H100/H200. A big MoE with 1M context window such as GLM-5.3 flash requires a lot of memory, and memory/tb on a trn2.48xlarge costs less than half compared to 8x h200 on AWS, and hence we wanted to experiment with it and now we’re sharing some early results. But AWS's own stack didn't support the model: vLLM Neuron's latest release did not register any GLM model, and NxDI, AWS's own distributed inference framework, is no longer under active development. We also saw the drop of SGLang Neuron implementation yesterday, but there is no good support for Trn2, which is the only chip available for public use right now. We ran semiAnalysis's AgentX benchmarks, which replays real coding agent sessions: - 1 box served 28.9 RPM(requests per minute) with 32 agents at batch 12 (also known as concurrency) -The P50 TTFT with a cached prompt at 16 agents is ~1.24 seconds with a decode of 35.9 tps. Initially, the recurrence in one kda (linear attention) layer was ~2% of the layer's attention time at batch 1, and the rest was projections, transposes and XLA glue between small kernels. So we wrote the megakernel so that it covers the whole layer in 2 kernel dispatch, which made decode 25% faster at batch 8. The sparse attention kernel keep a layer’s working weights in SBUF, distributing weighted streaming across the cores and handling the interchip communication within There’s an approximation in the sparse-attention prefill, affecting about 1.2% of block selections. You can refer to the write-up for the profiling results: https://runanywhere.ai/blog/glm-5-3-flash-trainium2-nki-mega... Please give it a try yourself on a trn2.48xlarge and reproduce the AgentX results by following the steps in docs/RESULTS.md. Happy to collaborate and hear any feedback. Deploying high performant dedicated inference at lab like performance and half the price for open models such as the GLM-5.3 family, Kimi K3, Deepseek flash etc. is how we make money. You can talk to us regarding the same at founders@runanywhere.ai. We hope you find this useful. If you are working with Trainium or have experience with NKI kernels, we'd love to get your honest feedback. Feel free to share the models you want support for next, and we welcome any contributions to the repository.

189

Cloudflare Joins the Jevolution and Labels Itself a Neolab

71

3 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · chưa có số tương tác · Nguồn crawl

Richard MacManus, ricmac và 1 nguồn khác 1 bài viết · Latent Space, X
Nguyên văn nguồn
Chi tiết nguồn

Cloudflare has been one of the essential infrastructure companies of the web for the past decade and a half. But now, it’s turning into a neolab — at least according to a presentation at AI Engineer Code Summit by Michelle Chen , who runs Cloudflare’s AI Platform on the product side. We’ll get into what exactly a neolab is in a minute (the short version: they build models and they’re not called OpenAI or Anthropic). Cloudflare is claiming to be one because it too has begun to launch models. Two System One models , to be precise: Clef and Clairic. As Chen explained in her talk, Clef is a decision model directly inspired by TypeSafe AI’s revolutionary Jev model , while Clairic is a new type of system one model that Cloudflare calls an “extract” model . In an interview with Latent Space after her presentation, Chen hinted that Cloudflare won’t just be producing system one models. There will be large language models, too. “We're not being a neolab [to] only launch system one models, even though it makes sense for our infrastructure. We've kind of entered this Pandora's box now, right? We opened it, now the possibilities are endless.” Chen said it’s “not just system one models, but potentially reasoning models that we've been experimenting with, and other LLMs and whatnot.” However, she added that these probably won’t be pre-trained models built from scratch, like the frontier labs produce. “I don't think that's our focus, but I think we can take existing resources out there and make [them] a lot more efficient and effective.” She noted that “most of our team really just does post-training,” so that will be the focus in model development. What is a neolab and is Cloudflare really one? The term neolab literally means a ‘new lab’ and it was coined last November by Stephanie Palazzolo from The Information, who defined it as “a new generation of research-focused AI startups.” Deedy Das , a partner at Menlo Ventures and an AI influencer, runs a big list of neolabs . It includes companies like Thinking Machines Lab, Poolside, and TypeSafe AI itself. According to Das, neolabs employ elite researchers, spend a lot of compute (“usually to train its own AI model”), don't have significant revenue traction, and they’re typically startups that have raised a lot of money. Deedy Das’ list of neolabs — note that TypeSafe is among the top 20. Cloudflare doesn’t tick at least half of those boxes, since it’s a public company with significant revenue traction . In fact, earlier this month Cloudflare announced record earnings . “The third quarter was Cloudflare's best quarter ever,” said CEO Matthew Prince . “We crossed $3 billion in annualized revenue with revenue of $782 million, up 39% year over year.” So Cloudflare as a “neolab” is pushing the accepted definition. However, as Chen argued in her presentation, building models is part of a natural progression for the company : from infrastructure, to compute (e.g. the Workers platform, including now for agents), to storage, to serving open weight models like Kimi, GLM and DeepSeek (on Workers AI), to now building its own models. Jev as the “east wind” Chen readily admits that Jev inspired Cloudflare’s pivot to building models. Referencing a Chinese proverb, she framed Jev’s arrival in September as “the east wind” that unexpectedly changed how Cloudflare viewed AI models. “And so when the system one and Jev paradigm started coming on board,” Chen said in her presentation, “we were like, this makes so much sense for us to adopt, right? We don't have to send every request to an LLM. We can send some of it to a System One model.” In our conversation, Chen commented on how it took only two weeks for them to build Clef — which is a copy of Jev — whereas it took TypeSafe AI two years to build Jev. She meant that as a compliment for how hard TypeSafe AI worked to create this new type of model. “All credit to TypeSafe, really, for actually attacking this space and inventing something new here , that people could relate to so strongly and be able to use it. And, yeah, we came up with a model super quickly, but they put in a lot of legwork and we knew exactly what the API schema should look like and whatnot.” Cloudflare is, at its core, still an infrastructure company — speed and low latency is its meat and potatoes. The main benefit of System One models, Chen remarked, is that they allow more work to be done by smaller, faster models , where output is measured in milliseconds rather than seconds. Clairic and what extraction models do While Clef was a clone of Jev, Cloudflare soon came up with an original twist on System One with Clairic , launched last month as “the first model in a new class: System One extraction models.” “What Clairic does is it can take unstructured input, and it can extract, compute, estimate and forecast values from those inputs,” Chen explained in her presentation. In our interview, Chen said that her team wanted to use System One principles to find other areas where LLMs were “overkill” and didn’t always return the right answer. One of the problems they settled on was that LLMs don’t always deal well with unstructured input. Because LLMs are autoregressive, Chen explained, they are prone to hallucinate and they sometimes return malformed JSON. “So we used the same System One principles [as Jev/Clef] there, and decided on extraction.” Some examples of system one use cases at Cloudflare. She used the example of an invoice, where an LLM will sometimes get an important detail wrong — like the order number. “When you send it [the order] to an LLM, they're like, wait, I think the order number's three, maybe it's four, maybe it's five. But it's like, the number's right there, you just have to read it! ” So the idea with Clairic is that it will extract a typed value — like a number — from unstructured data, in one forward pass. Why Cloudflare is in the lab now Using the label “neolab” sounds a bit like a marketing gimmick, but it also makes a ton of sense

190

Show HN: An API for word timestamps from speech, 75% within 20ms

57

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 38 tương tác đã đo · Nguồn crawl

jasperstory 1 bài viết · HN: LLM
Nguyên văn nguồn
Chi tiết nguồn

Hey HN, we're Yarn (W24) and we make a video editing app for startups, and we built Quebec ( https://quebec.yarn.so ), an API that gives you accurate word timestamps from speech. We needed it because cutting a word even 50ms off from its true timing can ruin talking head footage (examples in the write up). Accurate word timestamps usually come from a forced aligner, which takes the speech audio and a transcript and works out exactly when each word starts and ends. We weren't satisfied with the accuracy of Montreal Forced Aligner (MFA) or new models like ElevenLabs Cue ( https://elevenlabs.io/blog/cue-aligner ). Giving LLMs access to a waveform/spectrogram didn't help much either. So we built our own. There are two particularly interesting parts: - We wrote our own decoder around MFA's acoustic model that only lets each word land within 200ms of the rough timings. That made search small enough to solve exactly, so we don't need to use MFA's beam search. - We added a small CNN, built on the first two layers of Whisper Tiny, that nudges each word boundary by up to 50ms. We couldn't find enough hand-labelled speech that allowed for commercial use, so we had Gemini label our own (17k word boundaries). It took a couple of hours and cost under $200. A net trained on Gemini's labels scored the same as one trained on human labels (73.9% vs. 74%). One way to measure accuracy is % of word boundaries within 20ms of hand labels. Here are the results on Buckeye (hand-labelled American speech that we didn't train on): - Quebec 75% - MFA 61% - ElevenLabs Cue 30% If you want to try it, it's free until tomorrow night. You can point your agent at our docs at https://quebec.yarn.so , and send audio on its own or with your own transcript. After that, it costs $0.32 per hour with no signup (minimum $10 top-up). We serve it at cost. Caveats: only tested in English and slower than ElevenLabs. Let us know if Quebec works well for you, and send us any samples that work badly (you can email support at yarn dot so). Also let us know if you've built or found a better aligner. In theory we would just switch to a better aligner, although we would probably just push a bit harder to make ours better. Thanks! Jasper

191

LangChain Raises $300M Series C at $3B Valuation

71

3 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · chưa có số tương tác · Nguồn crawl

langchain, hwchase17 và 1 nguồn khác 1 bài viết · LangChain Blog, X
Biên tập tiếng Việt
Chi tiết nguồn

LangChain raises $300M Series C at a $3B valuation, led by CapitalG, to help every company own its intelligence with LangSmith, the agent engineering platform.

LangChain raises $300M Series C at a $3B valuation, led by CapitalG, to help every company own its intelligence with LangSmith, the agent engineering platform.

  • LangChain raises $300M Series C at a $3B valuation, led by CapitalG, to help every company own its intelligence with LangSmith, the agent engineering platform.
  • LangChain raises $300M Series C at a $3B valuation, led by CapitalG
  • to help every company own its intelligence with LangSmith, the agent engineering platform.
195

The Resolution Hypothesis: Agent Evolution's Key Is Identifying Improvements

68

11 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 14 tương tác đã đo · Nguồn crawl

Yuanhao Zeng, Shaocheng Lan và 9 nguồn khác 1 bài viết · Hugging Face Papers
Biên tập tiếng Việt
Chi tiết nguồn

Bài báo mô tả vòng lặp tiến hóa tác nhân: proposer tạo các ứng viên (prompts, skills, memories) và selection chọn những ứng viên có điểm cao hơn. Tuy vậy, họ nói rằng evolution có thể thất bại khi khởi động trên một số tác vụ vì đánh giá nhiễu không thể phân biệt đáng tin cậy giữa ứng viên tốt và xấu.

Agent evolution follows a simple loop: a proposer writes candidate artifacts (prompts, skills, memories) and selection accepts those that score higher. This loop has shown promise, yet practitioners face a puzzle: methods trade wins across papers, and evolution often fails to bootstrap on certain tasks. We trace this puzzle to the Resolution Hypothesis: agent evolution stalls not because methods fail to propose better artifacts, but because noisy evaluations cannot reliably identify them. Across seven evolution methods and six models (over 10M LLM calls), we find support for the hypothesis at both levels where evaluation scores are used. At the candidate level (choosing artifacts), helpful candidate artifacts exist, but selection is no better than random at telling them from harmful ones, so errors accumulate across rounds. At the method level (ranking methods), typical margins of a few percentage points are smaller than the difference between two independent runs of the same method, so published rankings often rest on luck. Together, these findings indicate that agent evolution is often bottlenecked by reliably identifying improvements. This calls for a shift in how we develop and evaluate self-improving agents, from designing ever more candidate improvement systems to making true improvements detectable and accumulable.

  • We trace this puzzle to the Resolution Hypothesis: agent evolution stalls not because methods fail to propose better artifacts, but because noisy evaluations cannot reliably identify them.
  • We trace this puzzle to the Resolution Hypothesis: agent evolution stalls not because methods fail to propose better artifacts, but because noisy evaluations cannot reliably identify them.
  • Across seven evolution methods and six models (over 10M LLM calls), we find support for the hypothesis at both levels where evaluation scores are used.
  • Together, these findings indicate that agent evolution is often bottlenecked by reliably identifying improvements. This calls for a shift in how we develop and evaluate self-improving agents, from designing ever more candidate improvement systems to making true improvements detectable and accumulable.
196

Decoding Without a Decoder: Direct Pixel Prediction from Diffusion Transformers

67

7 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 9 tương tác đã đo · Nguồn crawl

Hansheng Chen, Shengqu Cai và 5 nguồn khác 1 bài viết · Hugging Face Papers
Nguyên văn nguồn
Chi tiết nguồn

Latent diffusion models rely on a decoder to map denoised latents to pixels, adding complexity and inference cost. We introduce Decoding Without a Decoder (DWD), which lets a finetuned diffusion transformer produce final pixels directly through a linear head. Unlike previous methods, where the denoising output leads to final pixels, DWD separates the two roles: the original denoising head continues to drive sampling, then the new DWD head predicts the pixels at the final step. We extend pretrained latent models with DWD efficiently by finetuning only the last few transformer blocks, training the DWD head with pixel quality losses while anchoring the denoising head to the pretrained model to preserve the sample trajectory. Across latent image and video generators, DWD removes the decoder and reduces inference cost while maintaining or even improving pixel quality. On Wan video generation, it visibly reduces detail distortion and flickering, lowering warping error by 23%. Remarkably, the same separation also improves pixel diffusion models that do not even use a decoder: a final-step DWD head produces substantially better texture detail in text-to-image generation, and improves ImageNet FID from 1.55 to 1.43, a new state of the art among pixel flow models.

197

QDA: Closed-Loop LLM Quantization Design with Agents

67

4 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 9 tương tác đã đo · Nguồn crawl

Xingyang Li, Tianlang Zhao và 2 nguồn khác 1 bài viết · Hugging Face Papers
Biên tập tiếng Việt
Chi tiết nguồn

Bài báo nêu rằng post-training quantization là cách tiêu chuẩn để phục vụ LLM với chi phí thấp, nhưng công thức quantization tốt phụ thuộc vào từng mô hình và độ chính xác, nên chuyên gia phải thiết kế lại cho mỗi mô hình. Họ giới thiệu QDA, nơi một agent thiết kế recipe cho từng mô hình và độ chính xác. QDA đánh giá nhanh bằng cách chấm candidate theo KL divergence đầu ra so với mô hình gốc trên reasoning traces mà agent không thấy, và kiểm tra thêm các candidate hứa hẹn bằng long generations để bắt lỗi như repetition loops.

Post-training quantization is the standard way to serve large language models at low cost. However, the best quantization recipe differs across models and precisions. As a result, experts must redesign it for every new model, which is time-consuming and often sub-optimal. Fortunately, an LLM agent can take over this design by refining the recipe over rounds of building and evaluating candidates, so that more rounds lead to better recipes. However, evaluating one quantized reasoning model takes tens of GPU-hours, and combining methods from different codebases means porting each to the new architecture by hand. We present QDA, a system in which an agent designs the recipe for each model and precision. To make evaluation fast, QDA scores each candidate in minutes by its output KL divergence from the original model on reasoning traces that the agent never sees, and checks promising ones with long generations to catch failures such as repetition loops. To make building fast, QDA provides a library of public PTQ methods that are compatible with one another and with new model architectures. Across four reasoning models, QDA improves accuracy over the strongest public recipe by 0.9, 1.4 and 2.2 percentage points on average at W4A16, W4A8 and W3A16, using 64 GPU-hours per search. On the 320B-parameter MoE model GLM-5.3-Flash at NVFP4 W4A4, it recovers 98.3% of the FP8 model's accuracy, against 96.9% for the best vendor checkpoint. Every QDA checkpoint also runs on existing serving kernels with no inference overhead. We will release the library, the evaluator and the harness.

  • Across four reasoning models, QDA improves accuracy over the strongest public recipe by 0.9, 1.4 and 2.2 percentage points on average at W4A16, W4A8 and W3A16, using 64 GPU-hours per search.
  • Across four reasoning models, QDA improves accuracy over the strongest public recipe by 0.9, 1.4 and 2.2 percentage points on average at W4A16, W4A8 and W3A16, using 64 GPU-hours per search.
  • On the 320B-parameter MoE model GLM-5.3-Flash at NVFP4 W4A4, it recovers 98.3% of the FP8 model's accuracy, against 96.9% for the best vendor checkpoint.
  • Every QDA checkpoint also runs on existing serving kernels with no inference overhead.
198

Let Samples Sing in Chorus: Mitigating Spurious Correlations via Cross-view Consensus

65

6 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 3 tương tác đã đo · Nguồn crawl

Weiwei Li, Junzhuo Liu và 4 nguồn khác 1 bài viết · Hugging Face Papers
Nguyên văn nguồn
Chi tiết nguồn

Deep models often rely on spurious correlations that fail on underrepresented groups. Existing methods either correct human-specified bias attributes or infer unknown biases from the learned representation space. However, annotated attributes may differ from the shortcuts actually used by a model, while a single representation provides incomplete and potentially noisy evidence. Our key insight is that a bias obscured in one feature space may be clearer in another. In this work, we propose CHORD (Cross-view Harmonic Outlier Reversal for Debiasing), a multi-view framework that allows samples to "sing in chorus" across diverse representation spaces to achieve robust cross-view consensus. CHORD aggregates aggregates within-class partitions in each view, which is a proxy for specifying candidate biases, to debias the target representation and classifier without bias supervision. Experiments on seven benchmarks across vision, language, speech, and medical imaging show consistent improvements in worst-group accuracy. Code and checkpoints are available at https://github.com/davelee-uestc/chord_debiasing_public .

199

Out of Sight, Still in Mind: Token Compression for Omni-LLMs

64

4 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 2 tương tác đã đo · Nguồn crawl

Suho Yoo, Youngjoon Jang và 2 nguồn khác 1 bài viết · Hugging Face Papers
Nguyên văn nguồn
Chi tiết nguồn

The goal of this paper is to reduce the input token cost of Omni-modal large language models (Omni-LLMs) at inference time. Omni-LLMs reason jointly over audio, video and text, but the cost of the three streams is highly unbalanced: visual tokens account for the vast majority of the input, and are highly redundant. In this paper, we propose ReMo, a training-free framework that compresses visual tokens by redistributing their information across modalities: a visual token is kept only if its information appears nowhere else. ReMo achieves this in two ways: (i) it aligns audio and video in a shared space via closed-form calibration, and removes visual tokens already explained by the audio or by other visual tokens; and (ii) it replaces object-level visual tokens, identified by a lightweight object detector, with compact text proxies, short descriptions of each object and its location, conveying the same content in far fewer tokens. On Qwen2.5-Omni at two model scales, ReMo removes 54% of the input tokens with comparable accuracy. It performs comparably to the full-token model, reaching 101.2% and 101.4% of its average accuracy over five audio-visual benchmarks.

200

NexSight: Verifiable Tasks for Fine-Grained Agentic Long-Video Understanding

64

4 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 2 tương tác đã đo · Nguồn crawl

Tianci Xie, Li Chen và 2 nguồn khác 1 bài viết · Hugging Face Papers
Biên tập tiếng Việt
Chi tiết nguồn

Bài báo nói rằng các câu hỏi chi tiết theo thời gian trong video dài có thể yêu cầu tìm các khoảnh khắc ngắn rải rác trong nhiều giờ. Việc đánh giá và học cho các mô hình tác nhân quyết định khi nào và nơi nào cần quan sát là khó vì bằng chứng thưa thớt có thể không đảm bảo đếm đúng hoặc không đủ để kiểm chứng toàn bộ dòng thời gian. Nhóm giới thiệu NexSight để xây dựng các tác vụ có thể kiểm chứng nhằm vừa đánh giá vừa huấn luyện hiểu video dài theo dạng tác nhân.

Fine-grained questions about long videos ask how many times an action occurs, in what order events unfold, or exactly when a state changes. Answering them can require finding brief moments scattered across hours of footage. Agentic models that decide when and where to look promise to find these moments, yet this ability is hard both to measure and to learn. Sparse supporting evidence may establish that an action occurred without establishing its total count; verifying timeline-wide claims requires checking for missed occurrences and double counting. Answer-only supervision, in turn, does not explicitly supervise the search for evidence. We present NexSight, which builds verifiable tasks to both evaluate and train agentic long-video understanding. Its agentic pipeline, SightForge, accepts a task only if a verifier blind to the draft answer can reconstruct it from evidence densely reacquired from the raw video and counterexample checks fail to refute it. This yields SightLine, 310 evidence-traceable tasks from 108 long videos, evaluated through SightLoop, a shared multiscale harness supporting temporal exploration, local inspection, evidence integration, and revisiting while recording returned observations. On disjoint videos, solver trajectories on verified tasks become step-level supervision for observation decisions. The strongest model reaches only 54.52% on SightLine, yet 79.35% when given the annotated evidence. With under 6K examples, Sight-35B nearly doubles its base model's interactive accuracy (21.29% to 42.26%), outperforms the 397B model of its family, begins using explicit spatial inspection after post-training, which its base model never uses, and gains over 8 points on two external long-video benchmarks.

  • This yields SightLine, 310 evidence-traceable tasks from 108 long videos, evaluated through SightLoop, a shared multiscale harness supporting temporal exploration, local inspection, evidence integration, and revisiting while recording returned observations.
  • This yields SightLine, 310 evidence-traceable tasks from 108 long videos, evaluated through SightLoop, a shared multiscale harness supporting temporal exploration, local inspection, evidence integration, and revisiting while recording returned observations.
  • The strongest model reaches only 54.52% on SightLine, yet 79.35% when given the annotated evidence.
  • With under 6K examples, Sight-35B nearly doubles its base model's interactive accuracy (21.29% to 42.26%), outperforms the 397B model of its family, begins using explicit spatial inspection after post-training, which its base model never uses, and gains over 8 points on two external long-video benchmarks.
181–200 / 206
Trang 10 / 11