Soujanya Poria

Soujanya Poria on Hugging Face Daily Papers: 37 papers, 3 in the top 3 of their day, 677 upvotes.

  1. BaRe-Mem: Bayesian Reliability Memory for Robust and Adaptive Agent Consultation 8 upvotes, #52 of 2026-09-29
  2. Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models 30 upvotes, #30 of 2026-09-29
  3. MemBodied: Recurrent Associative Memory for Vision-Language-Action Models 14 upvotes, #15 of 2026-09-24
  4. GE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation 59 upvotes, #8 of 2026-09-09
  5. MNIST-PRO: MNIST is Back as a Partially Observable World for AI Agents 8 upvotes, #22 of 2026-09-01
  6. ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step 11 upvotes, #27 of 2026-08-04
  7. Σ-Mem: An Online Reliability Memory for LLM-based Multi-Agent Systems 17 upvotes, #22 of 2026-07-31
  8. IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation 9 upvotes, #12 of 2026-07-27
  9. On the Limits of LLM-as-Judge for Scientific Novelty Assessment 3 upvotes, #36 of 2026-06-10
  10. GRAIL: Gradient-Reweighted Advantages for Reinforcement Learning with Verifiable Rewards 4 upvotes, #34 of 2026-06-03
  11. δ-mem: Efficient Online Memory for Large Language Models 119 upvotes, #3 of 2026-05-13
  12. From Perception to Action: An Interactive Benchmark for Vision Reasoning 22 upvotes, #5 of 2026-02-25
  13. Error-Free Linear Attention is a Free Lunch: Exact Solution from Continuous-Time Dynamics 39 upvotes, #9 of 2025-12-16
  14. NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards 11 upvotes, #13 of 2025-11-18
  15. 10 Open Challenges Steering the Future of Vision-Language-Action Models 5 upvotes, #21 of 2025-11-11
  16. Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics 4 upvotes, #30 of 2025-10-08
  17. Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons Learned 5 upvotes, #21 of 2025-10-02
  18. OffTopicEval: When Large Language Models Enter the Wrong Chat, Almost Always! 10 upvotes, #27 of 2025-10-01
  19. JAM: A Tiny Flow-based Song Generator with Fine-grained Controllability and Aesthetic Alignment 8 upvotes, #15 of 2025-07-29
  20. Harnessing Large Language Models for Scientific Novelty Detection 5 upvotes, #28 of 2025-06-02
  21. Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision 3 upvotes, #54 of 2025-05-27
  22. NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks 6 upvotes, #10 of 2025-04-29
  23. The Jumping Reasoning Curve? Tracking the Evolution of Reasoning Performance in GPT-[n] and o-[n] Models on Multimodal Puzzles 12 upvotes, #15 of 2025-02-04
  24. TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization 22 upvotes, #6 of 2024-12-31
  25. Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning 8 upvotes, #16 of 2024-12-17
  26. M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework 42 upvotes, #2 of 2024-11-12
  27. Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse 4 upvotes, #12 of 2024-09-18
  28. Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique 9 upvotes, #4 of 2024-08-21
  29. WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models 15 upvotes, #4 of 2024-08-08
  30. DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling 7 upvotes, #15 of 2024-06-24
  31. Reward Steering with Evolutionary Heuristics for Decoding-time Alignment 11 upvotes, #11 of 2024-06-24
  32. Ruby Teaming: Improving Quality Diversity Search with Memory for Automated Red Teaming 6 upvotes, #16 of 2024-06-24
  33. Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations 15 upvotes, #9 of 2024-06-19
  34. Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization 10 upvotes, #8 of 2024-04-16
  35. Contrastive Chain-of-Thought Prompting 35 upvotes, #3 of 2023-11-17
  36. Flacuna: Unleashing the Problem Solving Power of Vicuna using FLAN Fine-Tuning 23 upvotes, #4 of 2023-07-06
  37. INSTRUCTEVAL: Towards Holistic Evaluation of Instruction-Tuned Large Language Models 5 upvotes, #8 of 2023-06-09

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.