Research library
Search papers on equipment connectivity, quality inspection, production analysis, and manufacturing work.
Search and filter
New paper summaries
Summaries are editorial notes, not statements by the original authors. Check the original paper. Updated 2026-11-20.
- 219LLMs / NLP
Tokenisation via Convex Relaxations
- For the integer-only approach, linear programming selects only tokens it is almost certain about, meaning tokens with values of 0.999 or higher. This often yields a vocabulary smaller than the allowed budget.
- Proven optimality limit: now we know how much room remains to squeeze tokenization for compression. Since BPE is already within 1% of the limit at scale, researchers can focus more on other properties such as language morphology or robustness rather than compression.
- Non-greedy alternative: ConvexTok builds a vocabulary by considering the entire dataset at once, which makes better use of the vocabulary budget.
- 218AI / General
Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents
- Action realization failure, or 33.3 percent, occurs when the model has the right intent but fails to express it in an executable format, such as by omitting arguments, using the wrong delimiter, or generating free-form text instead of structured tool calls.
- Environment contract mismatch, or 23.2 percent, occurs when the model generates a syntactically valid action but violates the concrete rules of the tool or API, such as by accessing a non-existent database column or using an invalid flight code.
- Trajectory degeneration, or 33.6 percent, occurs when the agent falls into a degenerate state, such as repeating the same invalid action, stalling without progress, or failing to recover from an error even after receiving feedback.
- 217AI / General
Advancing Mathematics Research with AI-Driven Formal Proof Search
- Lemma hallucinations: Sometimes the agent claimed that a false lemma was a well-known result in the literature. Because the agent did not attempt to formally prove that specific lemma, the error was only discovered late in the process.
- Formalization as a filter: A formal proof assistant provides ground truth that makes AI-generated mathematics useful to researchers. It removes the need for humans to check basic logical errors.
- AI for strategy discovery: AI can help mathematicians by proposing high-level plans or identifying candidate counterexamples that humans might miss.
- 216Bioinformatics / Genomics
Scalable, Fast and Accurate Differential Gene Expression Testing from Millions of Cells of Multiple Patients
- Core problem: cells in single-cell RNA-seq are statistically dependent, which breaks the assumptions of traditional differential expression tests designed for independent bulk samples.
- Bayesian framework: it restores the independence structure at the patient level, cleanly separating inter-individual variation from true transcriptional differences.
- Multi-GPU variational inference enables computational scalability to more than 10 million cells across thousands of samples from clinical cohorts, atlas projects, and drug-response screens.
- Practical impact: it makes single-cell differential expression analysis possible at scale for the first time, without the computational bottlenecks or mathematical limitations of existing methods.
- 215AI Safety / Trust
Hallucinations Undermine Trust; Metacognition is a Way Forward
- The central argument is that most factuality gains come from expanding the boundary of knowledge, not from improving awareness of that boundary, meaning the distinction between what the model knows and does not know.
- The model may fundamentally lack the ability to separate truth from error, which creates an inherent tradeoff between removing hallucinations and preserving usefulness.
- The paper proposes faithful uncertainty, meaning that the model's linguistic uncertainty should match its intrinsic uncertainty, which offers a third path beyond either answering or refusing.
- For agent systems, uncertainty awareness becomes a control layer that governs when to explore, what to trust, and how to weight retrieved information.
- Empirical evidence, including poor generalization of truth probes, confident hallucinations, and failures of alignment methods, supports the existence of the discriminative gap.
- 214AI / General
MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems
- A rejection gate is implemented in a pre-call hook to block inefficient batching patterns.
- Root-cause remediation is possible because, by targeting the harness itself, MOSS can fix architectural flaws that text-based evolution cannot touch.
- Production usefulness comes from the integration of failure batching, test verification, and safe container replacement, which makes the idea of self-rewriting practical in real applications.
- 213Machine Learning
Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
- Surprisingly, these performance gains were achieved by training on only two full dialogue trajectories, which demonstrates the effectiveness of the RL paradigm.
- It shows strong performance on out-of-distribution benchmarks such as LongMemEval and MSC-Self-Instruct.
- The training gains observed on the 3B model transferred to the 7B model as well.
- 212Computer Vision
GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation
- Failure memory is a lesson about how to avoid failure.
- The prompt pool divides 20,000 requests into knowledge-anchored categories, such as facts and events, and quality-anchored categories, such as spatial composition and text layout.
- Teacher trajectories are created by using a strong model to generate initial successful trajectories and then having a VLM judge inspect them for correctness.
- 211AI / General
The Log is the Agent: Event-Sourced Reactive Graphs for Auditable, Forkable Agentic Systems
- The synthesizer writes the final memo in response to claims and evidence.
- Auditability is preserved because every state change has a clear causal parent and recorded model and tool interactions.
- Debugging becomes easier because developers can move to any point in the graph and branch execution to test a fix.
- 210AI / General
Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention
- On multi-key retrieval tasks, where several similar associations exist, Gated DeltaNet-2 showed a substantial advantage, confirming that separated gates help the model distinguish competing pieces of information within a fixed-size state.
- By selectively erasing specific channels, the model avoids overwriting or blurring existing stored data that may still be relevant when new information arrives.
- SWA handles local, fine-grained interactions within a small fixed window, such as the most recent 2,000 tokens.
- 209Machine Learning
TRINITY: An Evolved LLM Coordinator
- The core idea is that a compact coordinator, a 0.6B LLM plus a 10,000-parameter lightweight head, assigns Thinker, Worker, and Verifier roles on each turn and delegates work across multiple LLMs.
- Optimized with a separable covariance matrix adaptation evolution strategy (CMA-ES), it outperforms RL, imitation learning, and random search under high dimensionality and strict budget constraints.
- It achieves state of the art on standard benchmarks, including 86.2% on LiveCodeBench, and consistently outperforms individual models and existing multi-agent methods across coding, math, reasoning, and domain knowledge.
- The coordinator's hidden-state representation provides rich contextualization, and block-epsilon separability in the optimization landscape enables efficient evolutionary search.
- It generalizes robustly to out-of-distribution tasks without task-specific tuning.
- 208Machine Learning
You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories
- This paper demonstrates that RLVR weight trajectories are extremely low-rank and highly predictable.
- 207Computer Vision
ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop
- Directional bias: AI models often show confirmation bias, repeatedly choosing actions that confirm their initial impression rather than exploring new information, even though that initial impression may be wrong, and they often commit to an answer early in the process with high confidence regardless of whether the evidence is sufficient.
- Intelligent action planning: Develop an agent that can plan specialized trajectories to resolve spatial uncertainty.
- Uncertainty management and calibration: Build a model that can understand when it does not have enough information and adjust its confidence accordingly.
- 206Machine Learning
Vector Policy Optimization: Training for Diversity Improves Test-Time Search
- Maze Navigation is a synthetic task in which an agent must collect items such as gold and diamonds while avoiding lava hazards. Because the goals are deliberately conflicting, for example, gold is often near lava, it is a perfect testbed for validating Pareto-front coverage.
- MuSiQue is a multi-hop QA task that rewards both final answer accuracy and citation accuracy for intermediate reasoning steps.
- ToolRL is a function-calling benchmark in which the model must satisfy structural constraints while also achieving high attribute-level accuracy.
- 205Computer Vision
WorldKV: Efficient World Memory with World Retrieval and Compression
- Token pruning: tokens with high similarity scores are treated as redundant and discarded, and only the most distinctive tokens, the bottom P percent by similarity, are kept.
- LPIPS measures perceptual similarity, and lower is better.
- PSNR and SSIM measure signal and structural similarity, and higher is better.
- 204Computer Vision
MotiMotion: Motion-Controlled Video Generation with Visual Reasoning
- Semantic consistency measures how well a video matches the user's high-level intent.
- Accessibility is improved by reducing the need for manual frame-by-frame animation or precise technical specifications, which makes advanced video creation available to a broader range of users.
- Educational benchmarking gives the research community a specialized tool, MotiBench, that focuses on the logical and physical aspects of video generation rather than on visual fidelity alone.
- 203Machine Learning
Quantifying Hyperparameter Transfer and the Importance of Embedding Layer Learning Rate
- For LayerNorm learning rate, SP uses Θ(1/n), while μP uses Θ(1).
- For attention scaling, SP uses 1/d, and μP uses 1/d.
- The model is trained for a fixed number of iterations regardless of width.
- 202Computer Vision
Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving
- The paper shows that the method can handle edits with large changes in both geometry and appearance, which are difficult for existing methods.
- 201Computer Vision
Draw2Think: Harnessing Geometry Reasoning through Constraint Engine Interaction
- Construction fidelity is a model-level property that measures whether a VLM's intended construction matches the requirements of the problem.
- Explicit reading channel: observations showed that 74 to 91 percent of the system's derived answers included at least one value explicitly returned by the engine, confirming that the VLM actively uses the engine as a source of truth rather than relying only on its internal prior knowledge.
- Correction and replanning capability: after receiving an error message and using the object deletion tool, the model can correct its path. When a construction path leads to a contradiction or an invalid state, the model can backtrack and try an alternative strategy, just like a human mathematician using compass and straightedge.
- 200Computer Vision
Improved Baselines with Representation Autoencoders
- This paper identifies three insights from systematically examining several design choices to simplify and improve RAE.
- First, it studies a generalized formulation in which the representation is defined as the sum of the last k encoder layers, rather than only the final encoder layer.
- 199Machine Learning
Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning
- Maze-Unique: the authors found that task ambiguity is poison for attractor learning, because datasets with multiple valid solutions, such as different shortest paths in a maze, make it hard for the model to form stable attractors. They created a maze variant with a unique path and showed that EqR scales to solving complex 30x30 mazes with high confidence.
- Scale generalization: at test time, simply increasing the number of iterations lets the model generalize well beyond the complexity seen during training.
- Self-diagnosis: the fixed-point residual provides an intrinsic confidence score that does not require an external verifier.
- 198Computer Vision
Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
- Question generation: For each small region, the MLLM generates a question q that can be answered only by seeing the details inside that region.
- Grounding to the full image: The region's bounding box is overlaid on the full image I to form the student input x. A spatial instruction, such as 'look at the red box', is added to the question so the student knows where to focus.
- Crop generation: The region is cropped and resized, often by 2x, to form the teacher input x'.
- 197Computer Vision
Cambrian-P: Pose-Grounded Video Understanding
- Annotation: use the off-the-shelf pose estimator ViPE to generate external and internal camera parameters for the remaining clips.
- Model size: as the LLM size increases from 0.5B to 7B parameters, both VQA performance and pose accuracy improve consistently.
- Data size: increasing the amount of training data widens the performance gap between the pose-grounding model and the baseline.
- 196Computer Vision
Lance: Unified Multimodal Modeling by Multi-Task Synergy
- For understanding, generation helps: training on generative tasks such as video editing makes the model develop a deeper understanding of temporal dynamics and spatial relationships, which improves performance on video understanding benchmarks.
- For video generation, Lance scores 85.11 on VBench, the highest among unified models at the time of publication, with strong performance on object grounding and temporal consistency.
- For multimodal understanding, Lance scores 62.0 on MVBench, which evaluates temporal cognition and video reasoning. This is an 11.3% improvement over the next-best unified model, Show-o2 (7B).
- 195LLMs / NLP
HRM-Text: Efficient Pretraining Beyond Scaling
- In contrast, biological systems show highly sample-efficient learning through multi-timescale processing, such as the functional organization of frontoparietal loops.
- 194Machine Learning
CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs
- It maintains local state for operations such as the online log-sum-exp used in cross-entropy loss.
- It recovers a substantial portion of GPU time that would otherwise be lost to data movement.
- It provides a structured DSL that simplifies writing high-performance kernels.
- 193LLMs / NLP
Code as Agent Harness
- For semantic verification, code can easily be checked through tests for syntax and basic correctness, but it is still hard to verify whether the code actually satisfies the user's higher-level intent.
- Transactional state management ensures that multi-agent systems can handle complex, concurrent edits to a shared codebase without causing merge conflicts or inconsistent state.
- Human supervision is about developing an interface that lets humans inspect and intervene on the agents' internal code outputs without breaking the automation loop.
- 192Machine Learning
A Bitter Lesson for Data Filtering
- Use a fixed number of epochs and train for four epochs.
- Simplify the pipeline. Instead of spending thousands of GPU hours and a lot of human engineering effort on complex classifiers and heuristic rules, simply increasing training time on raw parsed web data can yield better returns.
- Even trash has value. Robustness to mixed and random data suggests that, if the model is large enough, almost any data containing some statistical signal related to the target distribution can be useful.
- 191AI / General
Probabilistic Tiny Recursive Model
- Although powerful, deterministic recursion can converge to suboptimal solutions without any escape mechanism.
- A common workaround combines test-time task-specific input perturbation with answer aggregation through voting.
- 190AI / General
Generative Recursive Reasoning
- Majority voting selects the most common answer among a set of samples.
- Stochasticity shows that the probabilistic nature of latent states is a powerful tool for structured reasoning and overcomes determinism by preventing models from getting stuck in suboptimal deterministic trajectories.
- Width-based scaling introduces a way to expand reasoning performance by increasing the number of parallel samples, or width, instead of simply increasing sequence length or model size.
From research to product use
Operating capabilities, pilots, and technologies in development are identified separately.
View technology