MBPP
PulseAugur coverage of MBPP — every cluster mentioning MBPP across labs, papers, and developer communities, ranked by signal.
- used by GSM8K 70%
- instance of GSM8K 70%
- developed large-language models 70%
- developed by large-language models 70%
- instance of large-language models 70%
- instance of Gotit.pub 70%
- instance of ScienceCast 70%
- instance of CatalyzeX 70%
- used by Math-500 70%
- instance of DagsHub 70%
- instance of alphaXiv 70%
- competes with HumanEval 60%
8 day(s) with sentiment data
-
New method retrofits linear attention to speed up diffusion language models
Researchers have developed a method to retrofit linear attention into diffusion language models (dLLMs) to accelerate inference. This new approach, called block-hybrid attention, combines exact softmax attention within …
-
New AI method DELSCOUT tackles code deletion with scheduled proposals
Researchers have developed a novel approach called DELSCOUT for AI systems to remove redundant code, addressing the challenge of code bloat in large programming models. This method focuses on scheduling deletion candida…
-
New RAV framework boosts LLM code generation correctness
Researchers have developed RAV, a framework designed to enhance the functional correctness of code generated by large language models. RAV employs a three-stage process: task-aware prompt routing, aligned LoRA adaptatio…
-
Blind Resampling Outperforms Self-Repair in Small Code Models
A new research paper explores the effectiveness of different retry strategies for small code models, specifically comparing blind resampling against self-repair. The study found that blind resampling, which involves sim…
-
CodexGraph system enhances LLM interaction with code repositories
Researchers have developed CodexGraph, a novel system designed to improve how large language models (LLMs) interact with entire code repositories. Unlike existing methods that rely on similarity retrieval or task-specif…
-
Loop engineering for AI models is simple to wire but easy to get wrong
Loop engineering, a technique for improving AI model performance by creating iterative prompting structures, can be deceptively simple to implement but prone to subtle errors. Boris Cherny, who leads Claude Code at Anth…
-
DC-Leap framework accelerates dLLMs with training-free decoding
Researchers have introduced DC-Leap, a novel training-free framework designed to accelerate the inference speed of Diffusion Large Language Models (dLLMs). This method addresses the issue of conservative confidence thre…
-
New Mask-Aware Policy Gradients boost DLM reasoning on benchmarks · 2 sources tracked
Researchers have developed a novel approach called Mask-Aware Policy Gradients to enhance reasoning capabilities in Diffusion Language Models (DLMs). This method addresses the challenge of applying reinforcement learnin…
-
Research paper highlights flaws in AI code generation reward systems
A new research paper investigates the issue of "leaky" reward suites in Reinforcement Learning from Human Feedback (RLHF) for code generation. The study found that existing test suites contain persistent false positives…
-
New MRP technique boosts language model speed and accuracy
Researchers from Modal Research and NYU Shanghai's HeavyBall Research have developed a new technique called Multi-Token Residual Prediction (MRP) that enhances the speed and accuracy of language models. MRP works by tra…
-
AI code models improve via falsification, not just retries · 2 sources tracked
A new research paper explores the effectiveness of self-repair mechanisms in small, frozen code models. The study, which employed a placebo-controlled methodology, found that providing models with external, executable c…
-
LLM alignment for code generation: pretrained vs. fine-tuned models
Researchers have explored the effectiveness of Large Language Model (LLM) alignment techniques for code generation tasks, investigating whether alignment should start with a pretrained or a fine-tuned LLM. The study uti…
-
New methods boost LLM inference speed with adaptive decoding strategies
Researchers have developed BlockPilot, a novel approach to speculative decoding that adaptively predicts optimal block sizes for generating text. This method improves efficiency by learning a policy that selects block s…
-
New signature filtering method boosts LLM watermark detection accuracy
Researchers have developed a new method called signature filtering to improve the detection of statistical watermarks in large language models. This technique enhances existing watermark detection without altering the e…
-
Study finds most post-hoc operators fail to improve frozen code model accuracy
A new study published on arXiv investigates post-hoc falsification operators for small, frozen code models, finding that most operators do not improve accuracy over standard methods like Best-of-N. The research highligh…
-
Qwen2.5-Coder and DeepSeek-Coder V2 lead local coding LLM race
For users with 8GB of VRAM, the Qwen2.5-Coder 7B model is the top choice for coding tasks, offering impressive benchmark scores and a large context window. Those with 12-16GB of VRAM face a trade-off between a dense 14B…
-
New BrahmicTokenizer-131K improves Indic language tokenization efficiency
Researchers have developed BrahmicTokenizer-131K, a new tokenizer designed to improve efficiency for Indic languages while maintaining performance on English and code. This tokenizer achieves a 26.7% reduction in token …
-
New 'Poison-with-Style' Attack Targets Code LLMs with Subtle Triggers
Researchers have developed a novel data poisoning attack called Poison-with-Style (PwS) that targets code large language models (CLLMs). This attack subtly embeds trigger code styles within developers' prompts, causing …
-
New Bilevel Approach Enhances LLM Learning with Textual Feedback
Researchers have developed a novel bilevel approach for reinforcement learning with textual feedback, aiming to improve sample efficiency in LLMs. This new method, called Bilevel Natural Language Actor-Critic (Bi-NAC), …
-
New method steers LLM attention to correct reasoning errors
Researchers have developed Manifold-Guided Attention Steering (MAGS), a novel method to improve the reasoning capabilities of large language models. MAGS identifies deviations from a 'correctness manifold' in the model'…