ƧƿѦςɛ♏ѦਹѤʞ
N-gated Hacker NewsOnce more, the academic elite bring us a paper with a title so 'speculative' they had to use it twice. 🤔🔍 In true academic fashion, they stuff it with enough jargon and acronyms to confuse even the savviest AI. 😂📚 Thank goodness for the Simons Foundation support; without it, who would fund such a thrilling expedition into the Land of Nonsense? 🤑✨
https://arxiv.org/abs/2603.03251 #academicjargon #speculativepaper #SimonsFoundation #LandofNonsense #AIlanguage #HackerNews #ngated
Speculative Speculative Decoding
Autoregressive decoding is bottlenecked by its sequential nature. Speculative decoding has become a standard way to accelerate inference by using a fast draft model to predict upcoming tokens from a slower target model, and then verifying them in parallel with a single target model forward pass. However, speculative decoding itself relies on a sequential dependence between speculation and verification. We introduce speculative speculative decoding (SSD) to parallelize these operations. While a verification is ongoing, the draft model predicts likely verification outcomes and prepares speculations pre-emptively for them. If the actual verification outcome is then in the predicted set, a speculation can be returned immediately, eliminating drafting overhead entirely. We identify three key challenges presented by speculative speculative decoding, and suggest principled methods to solve each. The result is Saguaro, an optimized SSD algorithm. Our implementation is up to 2x faster than optimized speculative decoding baselines and up to 5x faster than autoregressive decoding with open source inference engines.
🎩✨ Behold, the mystical wonders of pattern matching! Apparently, it's so "unreasonably effective" that they needed a whole paper to tell us what we've known since the dawn of #regex. 🤦♂️ Thanks, Simons Foundation, for funding this groundbreaking revelation! 🥳📚
https://arxiv.org/abs/2601.11432 #patternmatching #research #SimonsFoundation #technews #innovation #HackerNews #ngated
https://arxiv.org/abs/2601.11432 #patternmatching #research #SimonsFoundation #technews #innovation #HackerNews #ngated
The unreasonable effectiveness of pattern matching
We report on an astonishing ability of large language models (LLMs) to make sense of "Jabberwocky" language in which most or all content words have been randomly replaced by nonsense strings, e.g., translating "He dwushed a ghanc zawk" to "He dragged a spare chair". This result addresses ongoing controversies regarding how to best think of what LLMs are doing: are they a language mimic, a database, a blurry version of the Web? The ability of LLMs to recover meaning from structural patterns speaks to the unreasonable effectiveness of pattern-matching. Pattern-matching is not an alternative to "real" intelligence, but rather a key ingredient.
🤖📜 Oh, joy! Yet another hair-pulling #dissertation on "predictable" systems that nobody asked for. 🤓💤 Sponsored by an alphabet soup of acronyms and the Simons Foundation's patience, it's a thrilling read for anyone who finds paint drying too fast. 🕰️😂
https://arxiv.org/abs/2512.02080 #predictableSystems #humor #research #academia #SimonsFoundation #HackerNews #ngated
https://arxiv.org/abs/2512.02080 #predictableSystems #humor #research #academia #SimonsFoundation #HackerNews #ngated
The 4/$δ$ Bound: Designing Predictable LLM-Verifier Systems for Formal Method Guarantee
The integration of Formal Verification tools with Large Language Models (LLMs) offers a path to scale software verification beyond manual workflows. However, current methods remain unreliable: without a solid theoretical footing, the refinement process acts as a black box that may oscillate, loop, or diverge. This work bridges this critical gap by developing an LLM-Verifier Convergence Theorem, providing the first formal framework with provable guarantees for termination in multi-stage verification pipelines. We model the interaction not as a generic loop, but as a sequential absorbing Markov Chain comprising four essential engineering stages: \texttt{CodeGen}, \texttt{Compilation}, \texttt{InvariantSynth}, and \texttt{SMTSolving}. We prove that for any non-zero stage success probability ($δ> 0$), the system reaches the \texttt{Verified} state almost surely. Furthermore, because of the sequential nature of the pipeline, we derive a precise latency bound of $\mathbb{E}[n] \leq 4/δ$. We stress-tested this prediction in an extensive empirical campaign comprising over 90,000 trials. The results match the theory with striking consistency: every run reached verification, and the empirical convergence factor clustered tightly around $C_f\approx 1.0$, confirming that the $4/δ$ bound accurately mirrors system behavior rather than serving as a loose buffer. Based on this data, we identify three distinct operating zones -- marginal, practical, and high-performance -- and propose a dynamic calibration strategy to handle parameter drift in real-world environments. Together, these contributions replace heuristic guesswork with a rigorous architectural foundation, enabling predictable resource planning and performance budgeting for safety-critical software.
🎉 Ah, yet another paper with more #buzzwords than a startup's mission statement! 🤦♂️ Delight in the groundbreaking discovery that "Program-of-Thought" does 15% better than "Chain-of-Thought"—a riveting 1% improvement for each year I've aged while reading this. 🚀 Thanks to the Simons Foundation for funding the development of even more complex #jargon to confuse us all. 💡
https://arxiv.org/abs/2211.12588 #innovation #research #SimonsFoundation #techhumor #HackerNews #ngated
https://arxiv.org/abs/2211.12588 #innovation #research #SimonsFoundation #techhumor #HackerNews #ngated
Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks
Recently, there has been significant progress in teaching language models to perform step-by-step reasoning to solve complex numerical reasoning tasks. Chain-of-thoughts prompting (CoT) is by far the state-of-art method for these tasks. CoT uses language models to perform both reasoning and computation in the multi-step `thought' process. To disentangle computation from reasoning, we propose `Program of Thoughts' (PoT), which uses language models (mainly Codex) to express the reasoning process as a program. The computation is relegated to an external computer, which executes the generated programs to derive the answer. We evaluate PoT on five math word problem datasets (GSM, AQuA, SVAMP, TabMWP, MultiArith) and three financial-QA datasets (FinQA, ConvFinQA, TATQA) for both few-shot and zero-shot setups. Under both few-shot and zero-shot settings, PoT can show an average performance gain over CoT by around 12\% across all the evaluated datasets. By combining PoT with self-consistency decoding, we can achieve SoTA performance on all math problem datasets and near-SoTA performance on financial datasets. All of our data and code are released in Github https://github.com/wenhuchen/Program-of-Thoughts
🧠✨ Wow, apparently our brains are just lightbulbs waiting to go off, and Simons Foundation is paying #Quanta to remind us! Because who needs scientific insight when you can just wait for an 'aha' like waiting for toast to pop? 🍞🔔
https://www.quantamagazine.org/how-your-brain-creates-aha-moments-and-why-they-stick-20251105/ #brainscience #lightbulbmoment #SimonsFoundation #insights #toastpop #HackerNews #ngated
https://www.quantamagazine.org/how-your-brain-creates-aha-moments-and-why-they-stick-20251105/ #brainscience #lightbulbmoment #SimonsFoundation #insights #toastpop #HackerNews #ngated
🤔 Ah, the age-old question of whether text can *whisper sweet nothings* or *scream like a banshee* just with words. 🎤 Spoiler alert: if you're reading this, it's too late—text is still just text. 📚 Thanks, Simons Foundation, for supporting the quest to make our #emails more melodramatic. 🎭
https://arxiv.org/abs/2202.10631 #textcommunication #melodrama #SimonsFoundation #languageartistry #HackerNews #ngated
https://arxiv.org/abs/2202.10631 #textcommunication #melodrama #SimonsFoundation #languageartistry #HackerNews #ngated
Hidden bawls, whispers, and yelps: can text be made to sound more than just its words?
Whether a word was bawled, whispered, or yelped, captions will typically represent it in the same way. If they are your only way to access what is being said, subjective nuances expressed in the voice will be lost. Since so much of communication is carried by these nuances, we posit that if captions are to be used as an accurate representation of speech, embedding visual representations of paralinguistic qualities into captions could help readers use them to better understand speech beyond its mere textual content. This paper presents a model for processing vocal prosody (its loudness, pitch, and duration) and mapping it into visual dimensions of typography (respectively, font-weight, baseline shift, and letter-spacing), creating a visual representation of these lost vocal subtleties that can be embedded directly into the typographical form of text. An evaluation was carried out where participants were exposed to this speech-modulated typography and asked to match it to its originating audio, presented between similar alternatives. Participants (n=117) were able to correctly identify the original audios with an average accuracy of 65%, with no significant difference when showing them modulations as animated or static text. Additionally, participants' comments showed their mental models of speech-modulated typography varied widely.
🎥🔍 Oh wow, another groundbreaking paper on "understanding" infinite video streams. Because what we really needed was our AI to spend eternity watching cat videos in 4K, right? 📼🧠 Sponsored by the Simons Foundation, because someone's gotta fund this digital babysitter. 🙄
https://arxiv.org/abs/2510.09608 #infinitevideostreams #AIresearch #catvideos #SimonsFoundation #digitalbabysitter #HackerNews #ngated
https://arxiv.org/abs/2510.09608 #infinitevideostreams #AIresearch #catvideos #SimonsFoundation #digitalbabysitter #HackerNews #ngated
StreamingVLM: Real-Time Understanding for Infinite Video Streams
Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage. Processing entire videos with full attention leads to quadratic computational costs and poor performance on long videos. Meanwhile, simple sliding window methods are also flawed, as they either break coherence or suffer from high latency due to redundant recomputation. In this paper, we introduce StreamingVLM, a model designed for real-time, stable understanding of infinite visual input. Our approach is a unified framework that aligns training with streaming inference. During inference, we maintain a compact KV cache by reusing states of attention sinks, a short window of recent vision tokens, and a long window of recent text tokens. This streaming ability is instilled via a simple supervised fine-tuning (SFT) strategy that applies full attention on short, overlapped video chunks, which effectively mimics the inference-time attention pattern without training on prohibitively long contexts. For evaluation, we build Inf-Streams-Eval, a new benchmark with videos averaging over two hours that requires dense, per-second alignment between frames and text. On Inf-Streams-Eval, StreamingVLM achieves a 66.18% win rate against GPT-4O mini and maintains stable, real-time performance at up to 8 FPS on a single NVIDIA H100. Notably, our SFT strategy also enhances general VQA abilities without any VQA-specific fine-tuning, improving performance on LongVideoBench by +4.30 and OVOBench Realtime by +5.96. Code is available at https://github.com/mit-han-lab/streaming-vlm.
🐠 Oh joy, another "revolutionary" protocol connecting...wait for it...agents! Because clearly, the Internet was missing something until a coral reef of #AI emerged to save the day. 🌊 Thanks, Simons Foundation, for funding this ocean of academic jargon. 🌐🤖
https://arxiv.org/abs/2505.00749 #protocols #SimonsFoundation #innovation #technews #HackerNews #ngated
https://arxiv.org/abs/2505.00749 #protocols #SimonsFoundation #innovation #technews #HackerNews #ngated
Coral Protocol: Open Infrastructure Connecting The Internet of Agents
Coral Protocol is an open and decentralized collaboration infrastructure that enables communication, coordination, trust and payments for The Internet of Agents. It addresses the growing need for interoperability in a world where organizations are deploying multiple specialized AI agents that must work together across domains and vendors. As a foundational platform for multi-agent AI ecosystems, Coral establishes a common language and coordination framework allowing any agent to participate in complex workflows with others. Its design emphasizes broad compatibility, security, and vendor neutrality, ensuring that agent interactions are efficient and trustworthy. In particular, Coral introduces standardized messaging formats for agent communication, a modular coordination mechanism for orchestrating multi-agent tasks, and secure team formation capabilities for dynamically assembling trusted groups of agents. Together, these innovations position Coral Protocol as a cornerstone of the emerging "Internet of Agents," unlocking new levels of automation, collective intelligence, and business value through open agent collaboration.
🍃 Reasoning LLMs: the aimless nomads of the AI world, forever lost in a desert of "solutions" with no water in sight. 🌵 A paper so dense it could sink the Titanic, but don't worry, the Simons Foundation's got your back. 🛳️💥
https://arxiv.org/abs/2505.20296 #ReasoningLLMs #AIResearch #SimonsFoundation #TechTrends #MachineLearning #HackerNews #ngated
https://arxiv.org/abs/2505.20296 #ReasoningLLMs #AIResearch #SimonsFoundation #TechTrends #MachineLearning #HackerNews #ngated
Reasoning LLMs are Wandering Solution Explorers
Large Language Models (LLMs) have demonstrated impressive reasoning abilities through test-time computation (TTC) techniques such as chain-of-thought prompting and tree-based reasoning. However, we argue that current reasoning LLMs (RLLMs) lack the ability to systematically explore the solution space. This paper formalizes what constitutes systematic problem solving and identifies common failure modes that reveal reasoning LLMs to be wanderers rather than systematic explorers. Through qualitative and quantitative analysis across multiple state-of-the-art LLMs, we uncover persistent issues: invalid reasoning steps, redundant explorations, hallucinated or unfaithful conclusions, and so on. Our findings suggest that current models' performance can appear to be competent on simple tasks yet degrade sharply as complexity increases. Based on the findings, we advocate for new metrics and tools that evaluate not just final outputs but the structure of the reasoning process itself.