Today

Trending in AI today

Today's trending AI news, launches and research from five sources people actually watch — Hacker News, Hugging Face, Product Hunt, arXiv and GitHub Trending — in one place, refreshed through the day.

Items right now: 237

Hacker News

58 items

1. Void: Open-source Cursor alternative

2. ALICE detects the conversion of lead into gold at the LHC

3. LegoGPT: Generating Physically Stable and Buildable Lego

4. NSF faces shake-up as officials abolish its 37 divisions

5. Business books are entertainment, not strategic tools

6. Rust’s dependencies are starting to worry me

7. Sofie: open-source web based system for automating live TV news production

8. Vision Now Available in Llama.cpp

9. Show HN: Hyvector – A fast and modern SVG editor

10. 21 GB/s CSV Parsing Using SIMD on AMD 9950X

11. Starlink User Terminal Teardown

12. Itter.sh – Micro-Blogging via Terminal

13. Progress toward fusion energy gain as measured against the Lawson criteria

14. CryptPad: An Alternative to the Google Suite

15. Show HN: Aberdeen – An elegant approach to reactive UIs

16. Data manipulations alleged in study that paved way for Microsoft's quantum chip

17. Audiobookshelf: Self-hosted audiobook and podcast server

18. All BART trains were stopped due to ‘computer networking problem’

19. WebGL Water (2010)

20. What’s new in Swift 6.2

21. Internet Roadtrip: Vote to steer

22. Brandon's Semiconductor Simulator

23. Gmail to SQLite

24. Fui: C library for interacting with the framebuffer in a TTY context

25. A Formal Analysis of Apple's iMessage PQ3 Protocol [pdf]

26. How to start a school with your friends

27. Launch HN: Nao Labs (YC X25) – Cursor for Data

28. A simple 16x16 dot animation from simple math rules

29. Fleurs du Mal

30. Past, present, and future of Sorbet type syntax

31. Implementing a Struct of Arrays

32. Odin, a Pragmatic C Alternative with a Go Flavour

33. Private Japanese lunar lander enters orbit around moon ahead of a June touchdown

34. Why 536 was 'the worst year to be alive' (2018)

35. Slow software for a burning world

36. Show HN: Oliphaunt – A native Mastodon client for macOS

37. New Tool: lsds – List All Linux Block Devices and Settings in One Place

38. The Linux Kernel's PGP Web of Trust

39. Reverse Engineering "DNA Sequences" in the Lost World: Jurassic Park Video Game

40. Show HN: A backend agnostic Ruby framework for building reactive desktop apps

41. Google Doc Templates for Startups

42. Zombieverter: Open source VCU for reusing salvage EV components

43. Not a three-year-old chimney sweep (2022)

44. Charles Bukowski, William Burroughs, and the Computer (2009)

45. Europe launches program to lure scientists away from the US

46. PlainBudget – Minimalist Plain Text Budgeting

47. Math Machine – A notebook will show your kid how far they have travelled

48. "Night of the Living Dead" accidentally became public domain (2019)

49. Inventing the Adventure Game (1984)

50. Show HN: Hyper – Standards-first React alternative

51. LTXVideo 13B AI video generation

52. Detect and crash Chromium bots

53. Some novelists are becoming video game writers – and vice-versa

54. Linear Programming for Fun and Profit

55. Show HN: BlenderQ – A TUI for managing multiple Blender renders

56. Show HN: Hydra (YC W22) – Serverless Analytics on Postgres

57. The birth of AI poker? Letters from the 1984 WSOP

58. Stratolaunch Successfully Completes Reusable Hypersonic Flight and Recovery

Hugging Face

60 items

1. ibm-granite/granite-4.0-tiny-preview

ibm-granite/granite-4.0-tiny-preview Text Generation · 1.74k Download · 92 Like

2. lusxvr/nanoVLM-222M

lusxvr/nanoVLM-222M Image-Text-to-Text · 496 Download · 53 Like

3. Qwen/Qwen3-0.6B

Qwen/Qwen3-0.6B Text Generation · 314k Download · 220 Like

4. deepseek-ai/DeepSeek-R1

deepseek-ai/DeepSeek-R1 Text Generation · 1.27M Download

5. Qwen/Qwen2.5-Omni-3B

Qwen/Qwen2.5-Omni-3B Any-to-Any · 16.4k Download · 188 Like

6. microsoft/Phi-4-reasoning

microsoft/Phi-4-reasoning Text Generation · 6.89k Download · 161 Like

7. tencent/Hunyuan3D-2

tencent/Hunyuan3D-2 Image-to-3D · 419k Download · 1.4k Like

8. HiDream-ai/HiDream-E1-Full

HiDream-ai/HiDream-E1-Full Any-to-Any · 3.84k Download · 143 Like

9. nvidia/parakeet-tdt-0.6b-v2

nvidia/parakeet-tdt-0.6b-v2 Automatic Speech Recognition · 72.7k Download · 659 Like

10. ACE-Step/ACE-Step-v1-3.5B

ACE-Step/ACE-Step-v1-3.5B Text-to-Audio · 287 Download

11. nari-labs/Dia-1.6B

nari-labs/Dia-1.6B Text-to-Speech · 148k Download

12. Lightricks/LTX-Video

Lightricks/LTX-Video Text-to-Video · 214k Download

13. deepseek-ai/DeepSeek-Prover-V2-671B

deepseek-ai/DeepSeek-Prover-V2-671B Text Generation · 7.38k Download

14. Qwen/Qwen3-235B-A22B

Qwen/Qwen3-235B-A22B Text Generation · 82.4k Download

15. JetBrains/Mellum-4b-base

JetBrains/Mellum-4b-base Text Generation · 2.81k Download · 304 Like

16. lodestones/Chroma

lodestones/Chroma Text-to-Image · 392 Download

17. Qwen/Qwen3-30B-A3B

Qwen/Qwen3-30B-A3B Text Generation · 150k Download

18. black-forest-labs/FLUX.1-dev

black-forest-labs/FLUX.1-dev Text-to-Image · 2.66M Download

19. cognition-ai/Kevin-32B

cognition-ai/Kevin-32B Updated 4 days ago · 87 Download

20. microsoft/Phi-4-reasoning-plus

microsoft/Phi-4-reasoning-plus Text Generation · 10.8k Download · 236 Like

21. Tesslate/UIGEN-T2-7B-Q8_0-GGUF

Tesslate/UIGEN-T2-7B-Q8_0-GGUF Text Generation · 2.59k Download · 113 Like

22. fdtn-ai/Foundation-Sec-8B

fdtn-ai/Foundation-Sec-8B Text Generation · 21.5k Download · 143 Like

23. nvidia/parakeet-tdt-0.6b-v2

nvidia/parakeet-tdt-0.6b-v2 Automatic Speech Recognition · 72.7k Download · 659 Like

24. ACE-Step/ACE-Step-v1-3.5B

ACE-Step/ACE-Step-v1-3.5B Text-to-Audio · 287 Download

25. nari-labs/Dia-1.6B

nari-labs/Dia-1.6B Text-to-Speech · 148k Download

26. Lightricks/LTX-Video

Lightricks/LTX-Video Text-to-Video · 214k Download

27. deepseek-ai/DeepSeek-Prover-V2-671B

deepseek-ai/DeepSeek-Prover-V2-671B Text Generation · 7.38k Download

28. Qwen/Qwen3-235B-A22B

Qwen/Qwen3-235B-A22B Text Generation · 82.4k Download

29. JetBrains/Mellum-4b-base

JetBrains/Mellum-4b-base Text Generation · 2.81k Download · 304 Like

30. lodestones/Chroma

lodestones/Chroma Text-to-Image · 392 Download

31. Qwen/Qwen3-30B-A3B

Qwen/Qwen3-30B-A3B Text Generation · 150k Download

32. black-forest-labs/FLUX.1-dev

black-forest-labs/FLUX.1-dev Text-to-Image · 2.66M Download

33. cognition-ai/Kevin-32B

cognition-ai/Kevin-32B Updated 4 days ago · 87 Download

34. microsoft/Phi-4-reasoning-plus

microsoft/Phi-4-reasoning-plus Text Generation · 10.8k Download · 236 Like

35. Tesslate/UIGEN-T2-7B-Q8_0-GGUF

Tesslate/UIGEN-T2-7B-Q8_0-GGUF Text Generation · 2.59k Download · 113 Like

36. fdtn-ai/Foundation-Sec-8B

fdtn-ai/Foundation-Sec-8B Text Generation · 21.5k Download · 143 Like

37. hexgrad/Kokoro-82M

hexgrad/Kokoro-82M Text-to-Speech · 1.88M Download

38. tencent/HunyuanCustom

tencent/HunyuanCustom Image-to-Video · 63 Download

39. Qwen/Qwen3-8B

Qwen/Qwen3-8B Text Generation · 394k Download · 259 Like

40. ServiceNow-AI/Apriel-Nemotron-15b-Thinker

ServiceNow-AI/Apriel-Nemotron-15b-Thinker Updated 4 days ago · 62 Download

41. XiaomiMiMo/MiMo-7B-RL

XiaomiMiMo/MiMo-7B-RL Text Generation · 5.9k Download · 242 Like

42. Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1

Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1 Text Generation · 427 Download · 63 Like

43. sanaka87/ICEdit-MoE-LoRA

sanaka87/ICEdit-MoE-LoRA Image-to-Image · 3.04k Download · 86 Like

44. ds4sd/SmolDocling-256M-preview

ds4sd/SmolDocling-256M-preview Image-Text-to-Text · 84.8k Download · 1.34k Like

45. hexgrad/Kokoro-82M

hexgrad/Kokoro-82M Text-to-Speech · 1.88M Download

46. tencent/HunyuanCustom

tencent/HunyuanCustom Image-to-Video · 63 Download

47. Qwen/Qwen3-8B

Qwen/Qwen3-8B Text Generation · 394k Download · 259 Like

48. ServiceNow-AI/Apriel-Nemotron-15b-Thinker

ServiceNow-AI/Apriel-Nemotron-15b-Thinker Updated 4 days ago · 62 Download

49. XiaomiMiMo/MiMo-7B-RL

XiaomiMiMo/MiMo-7B-RL Text Generation · 5.9k Download · 242 Like

50. Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1

Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1 Text Generation · 427 Download · 63 Like

51. sanaka87/ICEdit-MoE-LoRA

sanaka87/ICEdit-MoE-LoRA Image-to-Image · 3.04k Download · 86 Like

52. ds4sd/SmolDocling-256M-preview

ds4sd/SmolDocling-256M-preview Image-Text-to-Text · 84.8k Download · 1.34k Like

53. ibm-granite/granite-4.0-tiny-preview

ibm-granite/granite-4.0-tiny-preview Text Generation · 1.74k Download · 92 Like

54. lusxvr/nanoVLM-222M

lusxvr/nanoVLM-222M Image-Text-to-Text · 496 Download · 53 Like

55. Qwen/Qwen3-0.6B

Qwen/Qwen3-0.6B Text Generation · 314k Download · 220 Like

56. deepseek-ai/DeepSeek-R1

deepseek-ai/DeepSeek-R1 Text Generation · 1.27M Download

57. Qwen/Qwen2.5-Omni-3B

Qwen/Qwen2.5-Omni-3B Any-to-Any · 16.4k Download · 188 Like

58. microsoft/Phi-4-reasoning

microsoft/Phi-4-reasoning Text Generation · 6.89k Download · 161 Like

59. tencent/Hunyuan3D-2

tencent/Hunyuan3D-2 Image-to-3D · 419k Download · 1.4k Like

60. HiDream-ai/HiDream-E1-Full

HiDream-ai/HiDream-E1-Full Any-to-Any · 3.84k Download · 143 Like

Product Hunt

9 items

The first agentive art museum tour guide

2. Rubber Duck Armada

A fun clicker-game that's all about rubber ducks

Supercharge your browser with AI

Studio-level focus, detail, and clarity anywhere you shoot

Quantum-safe MCP servers for private, verifiable inference

6. AI Voice Cloning

Clone any voice in 3 seconds – hyper-realistic and free

Scan the world, collect aura points, compete with friends

Open-source AI for real-time, expressive voice role-play

9. Autograph Fair Offer

Estimate fair compensation for any role

arXiv

100 items

1. Generating Physically Stable and Buildable LEGO Designs from Text

Abstract: We introduce LegoGPT, the first approach for generating physically stable LEGO brick models from text prompts. To achieve this, we construct a… ▽ More | Submitted 8 May, 2025

2. StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant

Abstract: We present StreamBridge, a simple yet effective framework that seamlessly transforms offline Video-LLMs into streaming-capable models. It addresses two fundamental challenges in adapting existing… ▽ More | Submitted 8 May, 2025

3. ComPO: Preference Alignment via Comparison Oracles

Abstract: Direct alignment methods are increasingly used for aligning large… ▽ More | Submitted 8 May, 2025

4. Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging

Abstract: Vision-Language… ▽ More | Submitted 8 May, 2025

5. UKElectionNarratives: A Dataset of Misleading Narratives Surrounding Recent UK General Elections

Abstract: …the first dataset of human-annotated misleading narratives which circulated during the UK General Elections in 2019 and 2024. We also benchmark Pre-trained and Large Language Models (focusing on GPT-4o), studying their effectiveness in detecting election-related misleading narrat… ▽ More | Submitted 8 May, 2025

6. SITE: towards Spatial Intelligence Thorough Evaluation

Abstract: …to robotics. We introduce SITE, a benchmark dataset towards SI Thorough Evaluation in a standardized format of multi-choice visual question-answering, designed to assess large vision-… ▽ More | Submitted 8 May, 2025

7. Conversational Process Model Redesign

Abstract: With the recent success of large… ▽ More | Submitted 8 May, 2025

8. clem:todd: A Framework for the Systematic Benchmarking of LLM-Based Task-Oriented Dialogue System Realisations

Abstract: The emergence of instruction-tuned large… ▽ More | Submitted 8 May, 2025

9. MultiMind: Enhancing Werewolf Agents with Multimodal Reasoning and Theory of Mind

Abstract: Large… ▽ More | Submitted 8 May, 2025

10. GesPrompt: Leveraging Co-Speech Gestures to Augment LLM-Based Interaction in Virtual Reality

Abstract: Large Language Model (LLM)-based copilots have shown great potential in Extended Reality (XR) applications. However, the user faces challenges when describing the 3D environments to the copilots due to the complexity of conveying spatial-temporal information through text or speec… ▽ More | Submitted 8 May, 2025

11. EcoAgent: An Efficient Edge-Cloud Collaborative Multi-Agent Framework for Mobile Automation

Abstract: Cloud-based mobile agents powered by (multimodal) large language models ((M)LLMs) offer strong reasoning abilities but suffer from high latency and cost. While fine-tuned (M)SLMs enable edge deployment, they often lose general capabilities and struggle with complex tasks. To addr… ▽ More | Submitted 8 May, 2025

12. Ultra-FineWeb: Efficient Data Filtering and Verification for High-Quality LLM Training Data

Abstract: Data quality has become a key factor in enhancing model performance with the rapid development of large language models (LLMs). Model-driven data filtering has increasingly become a primary approach f… ▽ More | Submitted 8 May, 2025

13. TransProQA: an LLM-based literary Translation evaluation metric with Professional Question Answering

Abstract: The impact of Large… ▽ More | Submitted 8 May, 2025

14. Correctness Coverage Evaluation for Medical Multiple-Choice Question Answering Based on the Enhanced Conformal Prediction Framework

Abstract: Large… ▽ More | Submitted 8 May, 2025

15. Crosslingual Reasoning through Test-Time Scaling

Abstract: Reasoning capabilities of large… ▽ More | Submitted 8 May, 2025

16. Frame In, Frame Out: Do LLMs Generate More Biased News Headlines than Humans?

Abstract: Framing in media critically shapes public perception by selectively emphasizing some details while downplaying others. With the rise of large… ▽ More | Submitted 8 May, 2025

17. Let's Ask GNN: Empowering Large Language Model for Graph In-Context Learning

Abstract: Textual Attributed Graphs (TAGs) are crucial for modeling complex real-world systems, yet leveraging large language models (LLMs) for TAGs presents unique challenges due to the gap between sequential text processing and graph-structured dat… ▽ More | Submitted 8 May, 2025

18. TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining

Abstract: Large… ▽ More | Submitted 8 May, 2025

19. DSDrive: Distilling Large Language Model for Lightweight End-to-End Autonomous Driving with Unified Reasoning and Planning

Abstract: …vehicles into a unified framework. DSDrive leverages a compact LLM that employs a distillation method to preserve the enhanced reasoning capabilities of a larger-sized vision language… ▽ More | Submitted 8 May, 2025

20. Towards the Worst-case Robustness of Large Language Models

Abstract: Recent studies have revealed the vulnerability of large language models to adversarial attacks, where adversaries craft specific input sequences to induce harmful, violent, private, or incorrect outputs. In this work, we study their worst-case robustness, i.e., whether an adversa… ▽ More | Submitted 8 May, 2025

21. Hearing and Seeing Through CLIP: A Framework for Self-Supervised Sound Source Localization

Abstract: Large-scale vision-… ▽ More | Submitted 8 May, 2025

22. FLAM: Frame-Wise Language-Audio Modeling

Abstract: Recent multi-modal audio-language… ▽ More | Submitted 8 May, 2025

23. ICon: In-Context Contribution for Automatic Data Selection

Abstract: Data selection for instruction tuning is essential for improving the performance of Large… ▽ More | Submitted 8 May, 2025

24. Mapping User Trust in Vision Language Models: Research Landscape, Challenges, and Prospects

Abstract: The rapid adoption of Vision Language Models (VLMs), pre-trained on large image-text and video-text datasets, calls for protecting and informing users about when to trust these systems. This survey reviews studies on trust dynamics in user-VLM interactions, through a multi-discip… ▽ More | Submitted 8 May, 2025

25. Scalable Chain of Thoughts via Elastic Reasoning

Abstract: Large reasoning… ▽ More | Submitted 8 May, 2025

26. Toward Reasonable Parrots: Why Large Language Models Should Argue with Us by Design

Abstract: …paper, we advocate for the development of conversational technology that is inherently designed to support and facilitate argumentative processes. We argue that, at present, large language models (LLMs) are inadequate for this purpose, and we propose an ideal technology design ai… ▽ More | Submitted 8 May, 2025

27. HEXGEN-TEXT2SQL: Optimizing LLM Inference Request Scheduling for Agentic Text-to-SQL Workflow

Abstract: Recent advances in leveraging the agentic paradigm of large language models (LLMs) utilization have significantly enhanced Text-to-SQL capabilities, enabling users without specialized database expertise to query data intuitively. However, deploying these agentic LLM-based Text-to… ▽ More | Submitted 8 May, 2025

28. Software Development Life Cycle Perspective: A Survey of Benchmarks for CodeLLMs and Agents

Abstract: Code large… ▽ More | Submitted 8 May, 2025

29. A Two-Sample Test of Text Generation Similarity

Abstract: …across two groups of documents. The proposed test aims to assess text similarity by comparing the entropy of the documents. Entropy is estimated using neural network-based language… ▽ More | Submitted 8 May, 2025

30. Generating Symbolic World Models via Test-time Scaling of Large Language Models

Abstract: Solving complex planning problems requires Large… ▽ More | Submitted 8 May, 2025

31. PADriver: Towards Personalized Autonomous Driving

Abstract: In this paper, we propose PADriver, a novel closed-loop framework for personalized autonomous driving (PAD). Built upon Multi-modal Large Language Model (MLLM), PADriver takes streaming frames and personalized textual prompts as inputs. It autoaggressively performs scene understa… ▽ More | Submitted 8 May, 2025

32. Jailbreaking and Mitigation of Vulnerabilities in Large Language Models

Abstract: Large… ▽ More | Submitted 8 May, 2025

33. Latte: Transfering LLMs` Latent-level Knowledge for Few-shot Tabular Learning

Abstract: Few-shot tabular learning, in which machine learning models are trained with a limited amount of labeled data, provides a cost-effective approach to addressing real-world challenges. The advent of… ▽ More | Submitted 8 May, 2025

34. ChemRxivQuest: A Curated Chemistry Question-Answer Database Extracted from ChemRxiv Preprints

Abstract: …chemistry literature poses significant challenges for researchers seeking to efficiently access domain-specific knowledge. To support advancements in chemistry-focused natural language processing (NLP), we present ChemRxivQuest, a curated dataset of 970 high-quality question-answer (QA) pairs derived from 155 ChemRxiv preprints across 17 subfields of chemist… ▽ More | Submitted 8 May, 2025

35. QualBench: Benchmarking Chinese LLMs with Localized Professional Qualifications for Vertical Domain Evaluation

Abstract: The rapid advancement of Chinese large… ▽ More | Submitted 8 May, 2025

36. SmallPlan: Leverage Small Language Models for Sequential Path Planning with Simulation-Powered, LLM-Guided Distillation

Abstract: Efficient path planning in robotics, particularly within large-scale, dynamic environments, remains a significant hurdle. While… ▽ More | Submitted 8 May, 2025

37. Stealthy LLM-Driven Data Poisoning Attacks Against Embedding-Based Retrieval-Augmented Recommender Systems

Abstract: …constraints, and we examine their effectiveness in both promotion (long-tail items) and demotion (short-head items) scenarios. Our experiments on MovieLens, using two large language model (LLM) retrieval modules, show that even subtle attacks shift final rankings and item exposur… ▽ More | Submitted 8 May, 2025

38. Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks

Abstract: Text watermarking aims to subtly embed statistical signals into text by controlling the Large… ▽ More | Submitted 8 May, 2025

39. Biomed-DPT: Dual Modality Prompt Tuning for Biomedical Vision-Language Models

Abstract: Prompt learning is one of the most effective paradigms for adapting pre-trained vision-language… ▽ More | Submitted 8 May, 2025

40. MARK: Memory Augmented Refinement of Knowledge

Abstract: Large Language Models (LLMs) assist in specialized tasks but struggle to align with evolving domain knowledge without costly fine-tuning. Domain knowledge consists of: Knowledge: Immutable facts (e.g., 'A stone is solid') and generally accepted principles (e.g., ethical s… ▽ More | Submitted 8 May, 2025

41. Re-evaluating Open-ended Evaluation of Large Language Models

Abstract: Evaluation has traditionally focused on ranking candidates for a specific skill. Modern generalist models, such as… ▽ More | Submitted 8 May, 2025

42. Benchmarking Open-Source Large Language Models on Healthcare Text Classification Tasks

Abstract: The application of large… ▽ More | Submitted 8 May, 2025

43. Probabilistic Embeddings for Frozen Vision-Language Models: Uncertainty Quantification with Gaussian Process Latent Variable Models

Abstract: Vision-Language… ▽ More | Submitted 8 May, 2025

44. FedTDP: A Privacy-Preserving and Unified Framework for Trajectory Data Preparation via Federated Learning

Abstract: …(i) they do not address data privacy concerns, particularly in federated settings where trajectory data sharing is prohibited, and (ii) they typically design task-specific models that lack generalizability across diverse TDP scenarios. To overcome these challenges, we propose FedTDP, a privacy-preserving and unified framework that leverages the capabilities… ▽ More | Submitted 8 May, 2025

45. CacheFL: Efficient Federated Cache Model Fine-Tuning for Vision-Language Models

Abstract: Large pre-trained Vision-… ▽ More | Submitted 8 May, 2025

46. Faster, Cheaper, Better: Multi-Objective Hyperparameter Optimization for LLM and RAG Systems

Abstract: While Retrieval Augmented Generation (RAG) has emerged as a popular technique for improving Large… ▽ More | Submitted 8 May, 2025

47. Large Language Models Understanding: an Inherent Ambiguity Barrier

Abstract: A lively ongoing debate is taking place, since the extraordinary emergence of Large Language Models (LLMs) with regards to their capability to understand the world and capture the meaning of the dialogues in which they are involved. Arguments and counter-arguments have been propo… ▽ More | Submitted 8 May, 2025

48. Text2Cypher: Data Pruning using Hard Example Selection

Abstract: Database query languages such as SQL for relational databases and Cypher for graph databases have been widely adopted. Recent advancements in… ▽ More | Submitted 8 May, 2025

49. Enhancing Text2Cypher with Schema Filtering

Abstract: Knowledge graphs represent complex data using nodes, relationships, and properties. Cypher, a powerful query language for graph databases, enables efficient… ▽ More | Submitted 8 May, 2025

50. How Do Multimodal Large Language Models Handle Complex Multimodal Reasoning? Placing Them in An Extensible Escape Game

Abstract: The rapid advancing of Multimodal Large… ▽ More | Submitted 8 May, 2025

51. Generating Physically Stable and Buildable LEGO Designs from Text

Abstract: We introduce LegoGPT, the first approach for generating physically stable LEGO brick models from text prompts. To achieve this, we construct a… ▽ More | Submitted 8 May, 2025

52. StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant

Abstract: We present StreamBridge, a simple yet effective framework that seamlessly transforms offline Video-LLMs into streaming-capable models. It addresses two fundamental challenges in adapting existing… ▽ More | Submitted 8 May, 2025

53. ComPO: Preference Alignment via Comparison Oracles

Abstract: Direct alignment methods are increasingly used for aligning large… ▽ More | Submitted 8 May, 2025

54. Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging

Abstract: Vision-Language… ▽ More | Submitted 8 May, 2025

55. UKElectionNarratives: A Dataset of Misleading Narratives Surrounding Recent UK General Elections

Abstract: …the first dataset of human-annotated misleading narratives which circulated during the UK General Elections in 2019 and 2024. We also benchmark Pre-trained and Large Language Models (focusing on GPT-4o), studying their effectiveness in detecting election-related misleading narrat… ▽ More | Submitted 8 May, 2025

56. SITE: towards Spatial Intelligence Thorough Evaluation

Abstract: …to robotics. We introduce SITE, a benchmark dataset towards SI Thorough Evaluation in a standardized format of multi-choice visual question-answering, designed to assess large vision-… ▽ More | Submitted 8 May, 2025

57. Conversational Process Model Redesign

Abstract: With the recent success of large… ▽ More | Submitted 8 May, 2025

58. clem:todd: A Framework for the Systematic Benchmarking of LLM-Based Task-Oriented Dialogue System Realisations

Abstract: The emergence of instruction-tuned large… ▽ More | Submitted 8 May, 2025

59. MultiMind: Enhancing Werewolf Agents with Multimodal Reasoning and Theory of Mind

Abstract: Large… ▽ More | Submitted 8 May, 2025

60. GesPrompt: Leveraging Co-Speech Gestures to Augment LLM-Based Interaction in Virtual Reality

Abstract: Large Language Model (LLM)-based copilots have shown great potential in Extended Reality (XR) applications. However, the user faces challenges when describing the 3D environments to the copilots due to the complexity of conveying spatial-temporal information through text or speec… ▽ More | Submitted 8 May, 2025

61. EcoAgent: An Efficient Edge-Cloud Collaborative Multi-Agent Framework for Mobile Automation

Abstract: Cloud-based mobile agents powered by (multimodal) large language models ((M)LLMs) offer strong reasoning abilities but suffer from high latency and cost. While fine-tuned (M)SLMs enable edge deployment, they often lose general capabilities and struggle with complex tasks. To addr… ▽ More | Submitted 8 May, 2025

62. Ultra-FineWeb: Efficient Data Filtering and Verification for High-Quality LLM Training Data

Abstract: Data quality has become a key factor in enhancing model performance with the rapid development of large language models (LLMs). Model-driven data filtering has increasingly become a primary approach f… ▽ More | Submitted 8 May, 2025

63. TransProQA: an LLM-based literary Translation evaluation metric with Professional Question Answering

Abstract: The impact of Large… ▽ More | Submitted 8 May, 2025

64. Correctness Coverage Evaluation for Medical Multiple-Choice Question Answering Based on the Enhanced Conformal Prediction Framework

Abstract: Large… ▽ More | Submitted 8 May, 2025

65. Crosslingual Reasoning through Test-Time Scaling

Abstract: Reasoning capabilities of large… ▽ More | Submitted 8 May, 2025

66. Frame In, Frame Out: Do LLMs Generate More Biased News Headlines than Humans?

Abstract: Framing in media critically shapes public perception by selectively emphasizing some details while downplaying others. With the rise of large… ▽ More | Submitted 8 May, 2025

67. Let's Ask GNN: Empowering Large Language Model for Graph In-Context Learning

Abstract: Textual Attributed Graphs (TAGs) are crucial for modeling complex real-world systems, yet leveraging large language models (LLMs) for TAGs presents unique challenges due to the gap between sequential text processing and graph-structured dat… ▽ More | Submitted 8 May, 2025

68. TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining

Abstract: Large… ▽ More | Submitted 8 May, 2025

69. DSDrive: Distilling Large Language Model for Lightweight End-to-End Autonomous Driving with Unified Reasoning and Planning

Abstract: …vehicles into a unified framework. DSDrive leverages a compact LLM that employs a distillation method to preserve the enhanced reasoning capabilities of a larger-sized vision language… ▽ More | Submitted 8 May, 2025

70. Towards the Worst-case Robustness of Large Language Models

Abstract: Recent studies have revealed the vulnerability of large language models to adversarial attacks, where adversaries craft specific input sequences to induce harmful, violent, private, or incorrect outputs. In this work, we study their worst-case robustness, i.e., whether an adversa… ▽ More | Submitted 8 May, 2025

71. Hearing and Seeing Through CLIP: A Framework for Self-Supervised Sound Source Localization

Abstract: Large-scale vision-… ▽ More | Submitted 8 May, 2025

72. FLAM: Frame-Wise Language-Audio Modeling

Abstract: Recent multi-modal audio-language… ▽ More | Submitted 8 May, 2025

73. ICon: In-Context Contribution for Automatic Data Selection

Abstract: Data selection for instruction tuning is essential for improving the performance of Large… ▽ More | Submitted 8 May, 2025

74. Mapping User Trust in Vision Language Models: Research Landscape, Challenges, and Prospects

Abstract: The rapid adoption of Vision Language Models (VLMs), pre-trained on large image-text and video-text datasets, calls for protecting and informing users about when to trust these systems. This survey reviews studies on trust dynamics in user-VLM interactions, through a multi-discip… ▽ More | Submitted 8 May, 2025

75. Scalable Chain of Thoughts via Elastic Reasoning

Abstract: Large reasoning… ▽ More | Submitted 8 May, 2025

76. Toward Reasonable Parrots: Why Large Language Models Should Argue with Us by Design

Abstract: …paper, we advocate for the development of conversational technology that is inherently designed to support and facilitate argumentative processes. We argue that, at present, large language models (LLMs) are inadequate for this purpose, and we propose an ideal technology design ai… ▽ More | Submitted 8 May, 2025

77. HEXGEN-TEXT2SQL: Optimizing LLM Inference Request Scheduling for Agentic Text-to-SQL Workflow

Abstract: Recent advances in leveraging the agentic paradigm of large language models (LLMs) utilization have significantly enhanced Text-to-SQL capabilities, enabling users without specialized database expertise to query data intuitively. However, deploying these agentic LLM-based Text-to… ▽ More | Submitted 8 May, 2025

78. Software Development Life Cycle Perspective: A Survey of Benchmarks for CodeLLMs and Agents

Abstract: Code large… ▽ More | Submitted 8 May, 2025

79. A Two-Sample Test of Text Generation Similarity

Abstract: …across two groups of documents. The proposed test aims to assess text similarity by comparing the entropy of the documents. Entropy is estimated using neural network-based language… ▽ More | Submitted 8 May, 2025

80. Generating Symbolic World Models via Test-time Scaling of Large Language Models

Abstract: Solving complex planning problems requires Large… ▽ More | Submitted 8 May, 2025

81. PADriver: Towards Personalized Autonomous Driving

Abstract: In this paper, we propose PADriver, a novel closed-loop framework for personalized autonomous driving (PAD). Built upon Multi-modal Large Language Model (MLLM), PADriver takes streaming frames and personalized textual prompts as inputs. It autoaggressively performs scene understa… ▽ More | Submitted 8 May, 2025

82. Jailbreaking and Mitigation of Vulnerabilities in Large Language Models

Abstract: Large… ▽ More | Submitted 8 May, 2025

83. Latte: Transfering LLMs` Latent-level Knowledge for Few-shot Tabular Learning

Abstract: Few-shot tabular learning, in which machine learning models are trained with a limited amount of labeled data, provides a cost-effective approach to addressing real-world challenges. The advent of… ▽ More | Submitted 8 May, 2025

84. ChemRxivQuest: A Curated Chemistry Question-Answer Database Extracted from ChemRxiv Preprints

Abstract: …chemistry literature poses significant challenges for researchers seeking to efficiently access domain-specific knowledge. To support advancements in chemistry-focused natural language processing (NLP), we present ChemRxivQuest, a curated dataset of 970 high-quality question-answer (QA) pairs derived from 155 ChemRxiv preprints across 17 subfields of chemist… ▽ More | Submitted 8 May, 2025

85. QualBench: Benchmarking Chinese LLMs with Localized Professional Qualifications for Vertical Domain Evaluation

Abstract: The rapid advancement of Chinese large… ▽ More | Submitted 8 May, 2025

86. SmallPlan: Leverage Small Language Models for Sequential Path Planning with Simulation-Powered, LLM-Guided Distillation

Abstract: Efficient path planning in robotics, particularly within large-scale, dynamic environments, remains a significant hurdle. While… ▽ More | Submitted 8 May, 2025

87. Stealthy LLM-Driven Data Poisoning Attacks Against Embedding-Based Retrieval-Augmented Recommender Systems

Abstract: …constraints, and we examine their effectiveness in both promotion (long-tail items) and demotion (short-head items) scenarios. Our experiments on MovieLens, using two large language model (LLM) retrieval modules, show that even subtle attacks shift final rankings and item exposur… ▽ More | Submitted 8 May, 2025

88. Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks

Abstract: Text watermarking aims to subtly embed statistical signals into text by controlling the Large… ▽ More | Submitted 8 May, 2025

89. Biomed-DPT: Dual Modality Prompt Tuning for Biomedical Vision-Language Models

Abstract: Prompt learning is one of the most effective paradigms for adapting pre-trained vision-language… ▽ More | Submitted 8 May, 2025

90. MARK: Memory Augmented Refinement of Knowledge

Abstract: Large Language Models (LLMs) assist in specialized tasks but struggle to align with evolving domain knowledge without costly fine-tuning. Domain knowledge consists of: Knowledge: Immutable facts (e.g., 'A stone is solid') and generally accepted principles (e.g., ethical s… ▽ More | Submitted 8 May, 2025

91. Re-evaluating Open-ended Evaluation of Large Language Models

Abstract: Evaluation has traditionally focused on ranking candidates for a specific skill. Modern generalist models, such as… ▽ More | Submitted 8 May, 2025

92. Benchmarking Open-Source Large Language Models on Healthcare Text Classification Tasks

Abstract: The application of large… ▽ More | Submitted 8 May, 2025

93. Probabilistic Embeddings for Frozen Vision-Language Models: Uncertainty Quantification with Gaussian Process Latent Variable Models

Abstract: Vision-Language… ▽ More | Submitted 8 May, 2025

94. FedTDP: A Privacy-Preserving and Unified Framework for Trajectory Data Preparation via Federated Learning

Abstract: …(i) they do not address data privacy concerns, particularly in federated settings where trajectory data sharing is prohibited, and (ii) they typically design task-specific models that lack generalizability across diverse TDP scenarios. To overcome these challenges, we propose FedTDP, a privacy-preserving and unified framework that leverages the capabilities… ▽ More | Submitted 8 May, 2025

95. CacheFL: Efficient Federated Cache Model Fine-Tuning for Vision-Language Models

Abstract: Large pre-trained Vision-… ▽ More | Submitted 8 May, 2025

96. Faster, Cheaper, Better: Multi-Objective Hyperparameter Optimization for LLM and RAG Systems

Abstract: While Retrieval Augmented Generation (RAG) has emerged as a popular technique for improving Large… ▽ More | Submitted 8 May, 2025

97. Large Language Models Understanding: an Inherent Ambiguity Barrier

Abstract: A lively ongoing debate is taking place, since the extraordinary emergence of Large Language Models (LLMs) with regards to their capability to understand the world and capture the meaning of the dialogues in which they are involved. Arguments and counter-arguments have been propo… ▽ More | Submitted 8 May, 2025

98. Text2Cypher: Data Pruning using Hard Example Selection

Abstract: Database query languages such as SQL for relational databases and Cypher for graph databases have been widely adopted. Recent advancements in… ▽ More | Submitted 8 May, 2025

99. Enhancing Text2Cypher with Schema Filtering

Abstract: Knowledge graphs represent complex data using nodes, relationships, and properties. Cypher, a powerful query language for graph databases, enables efficient… ▽ More | Submitted 8 May, 2025

100. How Do Multimodal Large Language Models Handle Complex Multimodal Reasoning? Placing Them in An Extensible Escape Game

Abstract: The rapid advancing of Multimodal Large… ▽ More | Submitted 8 May, 2025

GitHub Trending

10 items

1. harry0703 / MoneyPrinterTurbo

利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM. | like: 28,430 fork: 4,175

2. Blaizzy / mlx-audio

A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon. | like: 1,386 fork: 95

3. voideditor / void

| like: 16,011 fork: 931

4. zed-industries / zed

Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter. | like: 58,937 fork: 4,122

5. Peterande / D-FINE

D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement [ICLR 2025 Spotlight] | like: 2,106 fork: 177

6. shane-mason / FieldStation42

Broadcast TV simulator | like: 398 fork: 19

7. wolfpld / tracy

Frame profiler | like: 11,466 fork: 786

8. Lightricks / LTX-Video

Official repository for LTX-Video | like: 4,429 fork: 363

9. longbridge / gpui-component

UI components for building fantastic desktop application by using GPUI. | like: 1,960 fork: 95

10. panaversity / learn-agentic-ai

Learn Agentic AI using Dapr Agentic Cloud Ascent (DACA) Design Pattern and Agent-Native Cloud Technologies: OpenAI Agents SDK, Memory, MCP, A2A, Knowledge Graphs, Dapr, Rancher Desktop, and Kubernetes. | like: 1,442 fork: 437